< Prev | Home | Model | Random | Next >

Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 4076 in Layer 19

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')



Text #0

Max Range: 13.2405. Min Range: -13.2405

Max Act: 13.2405. Min Act: -0.1700

Data Index: 8418857 (Open Web Text)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.9905. Min Act: -0.1700

Data Index: 3519509 (Open Web Text)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.9280. Min Act: -0.1700

Data Index: 5336937 (Open Web Text)

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.8030. Min Act: -0.1700

Data Index: 1379579 (Open Web Text)

Max Activating Token Index: 414

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.7405. Min Act: -0.1700

Data Index: 2806266 (Open Web Text)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.6155. Min Act: -0.1700

Data Index: 1000308 (Open Web Text)

Max Activating Token Index: 97

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.6155. Min Act: -0.1700

Data Index: 8744851 (Open Web Text)

Max Activating Token Index: 802

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.5530. Min Act: -0.1700

Data Index: 2980681 (Open Web Text)

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.5530. Min Act: -0.1700

Data Index: 5322048 (Open Web Text)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.5530. Min Act: -0.1700

Data Index: 2604981 (Open Web Text)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.4905. Min Act: -0.1700

Data Index: 1114081 (Open Web Text)

Max Activating Token Index: 549

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.4905. Min Act: -0.1700

Data Index: 2535385 (Open Web Text)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.4905. Min Act: -0.1700

Data Index: 5384701 (Open Web Text)

Max Activating Token Index: 818

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.4905. Min Act: -0.1700

Data Index: 6160283 (Open Web Text)

Max Activating Token Index: 244

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.4905. Min Act: -0.1700

Data Index: 863644 (Open Web Text)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.4280. Min Act: -0.1700

Data Index: 5321694 (Open Web Text)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.4280. Min Act: -0.1700

Data Index: 3793251 (Open Web Text)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.4280. Min Act: -0.1700

Data Index: 689722 (Open Web Text)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.3655. Min Act: -0.1700

Data Index: 8703208 (Open Web Text)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 13.2405. Min Range: -13.2405

Max Act: 12.4280. Min Act: -0.1700

Data Index: 3004381 (Open Web Text)

Max Activating Token Index: 499

Click toggle to see full text

Truncated

Full Text #19