< Prev | Home | Model | Random | Next >

Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 34 in Layer 17

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.8422. Min Act: -0.1700

Data Index: 3366287 (Open Web Text)

Max Activating Token Index: 869

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.6860. Min Act: -0.1700

Data Index: 6219934 (Open Web Text)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.5297. Min Act: -0.1700

Data Index: 1013580 (Open Web Text)

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.4672. Min Act: -0.1700

Data Index: 6682303 (Open Web Text)

Max Activating Token Index: 968

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.4672. Min Act: -0.1700

Data Index: 289441 (Open Web Text)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.3422. Min Act: -0.1700

Data Index: 4470375 (Open Web Text)

Max Activating Token Index: 242

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.3422. Min Act: -0.1700

Data Index: 8486054 (Open Web Text)

Max Activating Token Index: 361

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.3422. Min Act: -0.1700

Data Index: 6384288 (Open Web Text)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.2797. Min Act: -0.1700

Data Index: 97165 (Open Web Text)

Max Activating Token Index: 397

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.2797. Min Act: -0.1700

Data Index: 3019957 (Open Web Text)

Max Activating Token Index: 957

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.2485. Min Act: -0.1700

Data Index: 937607 (Open Web Text)

Max Activating Token Index: 281

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.2172. Min Act: -0.1700

Data Index: 7003801 (Open Web Text)

Max Activating Token Index: 174

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.1860. Min Act: -0.1700

Data Index: 1163850 (Open Web Text)

Max Activating Token Index: 849

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.2172. Min Act: -0.1700

Data Index: 568223 (Open Web Text)

Max Activating Token Index: 919

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.1860. Min Act: -0.1700

Data Index: 1525034 (Open Web Text)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.1547. Min Act: -0.1700

Data Index: 4802143 (Open Web Text)

Max Activating Token Index: 719

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.1547. Min Act: -0.1700

Data Index: 5632713 (Open Web Text)

Max Activating Token Index: 865

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.0297. Min Act: -0.1700

Data Index: 352662 (Open Web Text)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.0297. Min Act: -0.1700

Data Index: 2536625 (Open Web Text)

Max Activating Token Index: 949

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 7.8422. Min Range: -7.8422

Max Act: 7.0610. Min Act: -0.1700

Data Index: 4661212 (Open Web Text)

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #19