Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 498 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.6619. Min Act: -0.1700

Data Index: 7910934 (Open Web Text)

Max Activating Token Index: 915

Text #1

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.6819. Min Act: -0.1700

Data Index: 4499601 (Open Web Text)

Max Activating Token Index: 738

Text #2

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.6169. Min Act: -0.1700

Data Index: 6315682 (Open Web Text)

Max Activating Token Index: 592

Text #3

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.5829. Min Act: -0.1700

Data Index: 4792343 (Open Web Text)

Max Activating Token Index: 960

Text #4

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.5730. Min Act: -0.1700

Data Index: 2672867 (Open Web Text)

Max Activating Token Index: 835

Text #5

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.5122. Min Act: -0.1700

Data Index: 5624722 (Open Web Text)

Max Activating Token Index: 356

Text #6

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.5646. Min Act: -0.1700

Data Index: 5133123 (Open Web Text)

Max Activating Token Index: 92

Text #7

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.5109. Min Act: -0.1700

Data Index: 8006207 (Open Web Text)

Max Activating Token Index: 164

Text #8

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.5107. Min Act: -0.1700

Data Index: 122639 (Open Web Text)

Max Activating Token Index: 76

Text #9

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.4877. Min Act: -0.1700

Data Index: 4319574 (Open Web Text)

Max Activating Token Index: 197

Text #10

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.4466. Min Act: -0.1700

Data Index: 5820965 (Open Web Text)

Max Activating Token Index: 221

Text #11

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.5001. Min Act: -0.1700

Data Index: 3760356 (Open Web Text)

Max Activating Token Index: 528

Text #12

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.4326. Min Act: -0.1700

Data Index: 2590366 (Open Web Text)

Max Activating Token Index: 252

Text #13

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.4154. Min Act: -0.1700

Data Index: 2534173 (Open Web Text)

Max Activating Token Index: 274

Text #14

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.4470. Min Act: -0.1700

Data Index: 3852783 (Open Web Text)

Max Activating Token Index: 359

Text #15

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.4416. Min Act: -0.1700

Data Index: 8103232 (Open Web Text)

Max Activating Token Index: 576

Text #16

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.4374. Min Act: -0.1700

Data Index: 110398 (Open Web Text)

Max Activating Token Index: 338

Text #17

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.4250. Min Act: -0.1700

Data Index: 4143875 (Open Web Text)

Max Activating Token Index: 602

Text #18

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.4167. Min Act: -0.1700

Data Index: 1104278 (Open Web Text)

Max Activating Token Index: 570

Text #19

Max Range: 5.6819. Min Range: -5.6819

Max Act: 5.4119. Min Act: -0.1700

Data Index: 4841576 (Open Web Text)

Max Activating Token Index: 698