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

Dataset: Open Web Text

Neuron 1286 in Layer 0

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: 4.0587. Min Range: -4.0587

Max Act: 4.0587. Min Act: -0.1700

Data Index: 3270877 (Open Web Text)

Max Activating Token Index: 349

Text #1

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.9815. Min Act: -0.1700

Data Index: 7348146 (Open Web Text)

Max Activating Token Index: 476

Text #2

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.9551. Min Act: -0.1700

Data Index: 190712 (Open Web Text)

Max Activating Token Index: 377

Text #3

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.9400. Min Act: -0.1700

Data Index: 3557916 (Open Web Text)

Max Activating Token Index: 75

Text #4

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.9259. Min Act: -0.1700

Data Index: 3550069 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.9144. Min Act: -0.1700

Data Index: 4459546 (Open Web Text)

Max Activating Token Index: 263

Text #6

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.9291. Min Act: -0.1700

Data Index: 6041849 (Open Web Text)

Max Activating Token Index: 596

Text #7

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.9128. Min Act: -0.1700

Data Index: 2845595 (Open Web Text)

Max Activating Token Index: 695

Text #8

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.9439. Min Act: -0.1700

Data Index: 7219284 (Open Web Text)

Max Activating Token Index: 845

Text #9

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.9263. Min Act: -0.1700

Data Index: 5765898 (Open Web Text)

Max Activating Token Index: 68

Text #10

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.8875. Min Act: -0.1700

Data Index: 7348149 (Open Web Text)

Max Activating Token Index: 460

Text #11

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.8937. Min Act: -0.1700

Data Index: 1688064 (Open Web Text)

Max Activating Token Index: 988

Text #12

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.8546. Min Act: -0.1700

Data Index: 7594483 (Open Web Text)

Max Activating Token Index: 431

Text #13

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.8565. Min Act: -0.1700

Data Index: 8830278 (Open Web Text)

Max Activating Token Index: 422

Text #14

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.8593. Min Act: -0.1700

Data Index: 2920066 (Open Web Text)

Max Activating Token Index: 762

Text #15

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.8780. Min Act: -0.1700

Data Index: 6491887 (Open Web Text)

Max Activating Token Index: 819

Text #16

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.8580. Min Act: -0.1700

Data Index: 4525519 (Open Web Text)

Max Activating Token Index: 753

Text #17

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.8468. Min Act: -0.1700

Data Index: 3280667 (Open Web Text)

Max Activating Token Index: 971

Text #18

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.8193. Min Act: -0.1700

Data Index: 788566 (Open Web Text)

Max Activating Token Index: 857

Text #19

Max Range: 4.0587. Min Range: -4.0587

Max Act: 3.8257. Min Act: -0.1700

Data Index: 5284648 (Open Web Text)

Max Activating Token Index: 856