< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 6377 in Layer 46

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.8296. Min Act: -0.1700

Data Index: 7247978 (Open Web Text)

Max Activating Token Index: 97

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.7046. Min Act: -0.1700

Data Index: 8465873 (Open Web Text)

Max Activating Token Index: 541

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.6733. Min Act: -0.1700

Data Index: 4077236 (Open Web Text)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.6421. Min Act: -0.1700

Data Index: 2310186 (Open Web Text)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.5796. Min Act: -0.1700

Data Index: 3354394 (Open Web Text)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.5483. Min Act: -0.1700

Data Index: 7249114 (Open Web Text)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.5171. Min Act: -0.1700

Data Index: 2992435 (Open Web Text)

Max Activating Token Index: 762

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.4546. Min Act: -0.1700

Data Index: 32676 (Open Web Text)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.3921. Min Act: -0.1700

Data Index: 2966388 (Open Web Text)

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.3921. Min Act: -0.1700

Data Index: 7086623 (Open Web Text)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.3921. Min Act: -0.1700

Data Index: 8819738 (Open Web Text)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.3608. Min Act: -0.1700

Data Index: 2582910 (Open Web Text)

Max Activating Token Index: 326

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.3296. Min Act: -0.1700

Data Index: 2050452 (Open Web Text)

Max Activating Token Index: 245

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.3608. Min Act: -0.1700

Data Index: 3881275 (Open Web Text)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.2983. Min Act: -0.1700

Data Index: 5938617 (Open Web Text)

Max Activating Token Index: 214

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.2983. Min Act: -0.1700

Data Index: 1552042 (Open Web Text)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.2983. Min Act: -0.1700

Data Index: 1846438 (Open Web Text)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.2671. Min Act: -0.1700

Data Index: 1964361 (Open Web Text)

Max Activating Token Index: 155

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.2358. Min Act: -0.1700

Data Index: 8654768 (Open Web Text)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.8296. Min Range: -6.8296

Max Act: 6.2358. Min Act: -0.1700

Data Index: 6784163 (Open Web Text)

Max Activating Token Index: 793

Click toggle to see full text

Truncated

Full Text #19