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

Dataset: Open Web Text

Neuron 2055 in Layer 3

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: 4.0156. Min Range: -4.0156

Max Act: 4.0156. Min Act: -0.1700

Data Index: 8188330 (Open Web Text)

Max Activating Token Index: 916

Text #1

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.9487. Min Act: -0.1700

Data Index: 6103810 (Open Web Text)

Max Activating Token Index: 828

Text #2

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.9251. Min Act: -0.1700

Data Index: 6392520 (Open Web Text)

Max Activating Token Index: 437

Text #3

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.9646. Min Act: -0.1700

Data Index: 3158984 (Open Web Text)

Max Activating Token Index: 467

Text #4

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.9110. Min Act: -0.1700

Data Index: 6096817 (Open Web Text)

Max Activating Token Index: 971

Text #5

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.9570. Min Act: -0.1700

Data Index: 4875309 (Open Web Text)

Max Activating Token Index: 817

Text #6

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.9466. Min Act: -0.1700

Data Index: 7556394 (Open Web Text)

Max Activating Token Index: 448

Text #7

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.9344. Min Act: -0.1700

Data Index: 3299952 (Open Web Text)

Max Activating Token Index: 495

Text #8

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.9462. Min Act: -0.1700

Data Index: 3007107 (Open Web Text)

Max Activating Token Index: 657

Text #9

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.9094. Min Act: -0.1700

Data Index: 2094395 (Open Web Text)

Max Activating Token Index: 395

Text #10

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.9148. Min Act: -0.1700

Data Index: 1789146 (Open Web Text)

Max Activating Token Index: 580

Text #11

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.9100. Min Act: -0.1700

Data Index: 5557419 (Open Web Text)

Max Activating Token Index: 647

Text #12

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8678. Min Act: -0.1700

Data Index: 8749724 (Open Web Text)

Max Activating Token Index: 942

Text #13

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8958. Min Act: -0.1700

Data Index: 7425492 (Open Web Text)

Max Activating Token Index: 807

Text #14

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8539. Min Act: -0.1700

Data Index: 5158960 (Open Web Text)

Max Activating Token Index: 156

Text #15

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8737. Min Act: -0.1700

Data Index: 5440361 (Open Web Text)

Max Activating Token Index: 450

Text #16

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8863. Min Act: -0.1700

Data Index: 8805297 (Open Web Text)

Max Activating Token Index: 911

Text #17

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8549. Min Act: -0.1700

Data Index: 6534055 (Open Web Text)

Max Activating Token Index: 273

Text #18

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8597. Min Act: -0.1700

Data Index: 5175931 (Open Web Text)

Max Activating Token Index: 336

Text #19

Max Range: 4.0156. Min Range: -4.0156

Max Act: 3.8320. Min Act: -0.1700

Data Index: 5764129 (Open Web Text)

Max Activating Token Index: 496