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

Dataset: Open Web Text

Neuron 2479 in Layer 1

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: 2.1138. Min Range: -2.1138

Max Act: 2.0937. Min Act: -0.1700

Data Index: 412490 (Open Web Text)

Max Activating Token Index: 958

Text #1

Max Range: 2.1138. Min Range: -2.1138

Max Act: 2.1138. Min Act: -0.1700

Data Index: 1568124 (Open Web Text)

Max Activating Token Index: 924

Text #2

Max Range: 2.1138. Min Range: -2.1138

Max Act: 2.1039. Min Act: -0.1700

Data Index: 4006968 (Open Web Text)

Max Activating Token Index: 970

Text #3

Max Range: 2.1138. Min Range: -2.1138

Max Act: 2.0927. Min Act: -0.1700

Data Index: 5780843 (Open Web Text)

Max Activating Token Index: 994

Text #4

Max Range: 2.1138. Min Range: -2.1138

Max Act: 2.0721. Min Act: -0.1700

Data Index: 4969814 (Open Web Text)

Max Activating Token Index: 409

Text #5

Max Range: 2.1138. Min Range: -2.1138

Max Act: 2.0386. Min Act: -0.1700

Data Index: 868111 (Open Web Text)

Max Activating Token Index: 410

Text #6

Max Range: 2.1138. Min Range: -2.1138

Max Act: 2.0269. Min Act: -0.1700

Data Index: 7511637 (Open Web Text)

Max Activating Token Index: 389

Text #7

Max Range: 2.1138. Min Range: -2.1138

Max Act: 2.0216. Min Act: -0.1700

Data Index: 8182927 (Open Web Text)

Max Activating Token Index: 337

Text #8

Max Range: 2.1138. Min Range: -2.1138

Max Act: 2.0142. Min Act: -0.1700

Data Index: 8209275 (Open Web Text)

Max Activating Token Index: 1022

Text #9

Max Range: 2.1138. Min Range: -2.1138

Max Act: 2.0161. Min Act: -0.1700

Data Index: 251993 (Open Web Text)

Max Activating Token Index: 505

Text #10

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.9976. Min Act: -0.1700

Data Index: 3108870 (Open Web Text)

Max Activating Token Index: 146

Text #11

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.9886. Min Act: -0.1700

Data Index: 8504873 (Open Web Text)

Max Activating Token Index: 857

Text #12

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.9773. Min Act: -0.1700

Data Index: 4612377 (Open Web Text)

Max Activating Token Index: 59

Text #13

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.9819. Min Act: -0.1700

Data Index: 177389 (Open Web Text)

Max Activating Token Index: 87

Text #14

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.9877. Min Act: -0.1700

Data Index: 5019599 (Open Web Text)

Max Activating Token Index: 486

Text #15

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.9623. Min Act: -0.1700

Data Index: 3206856 (Open Web Text)

Max Activating Token Index: 906

Text #16

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.9727. Min Act: -0.1700

Data Index: 2209148 (Open Web Text)

Max Activating Token Index: 149

Text #17

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.9817. Min Act: -0.1700

Data Index: 5181262 (Open Web Text)

Max Activating Token Index: 182

Text #18

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.9803. Min Act: -0.1700

Data Index: 5596904 (Open Web Text)

Max Activating Token Index: 60

Text #19

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.9796. Min Act: -0.1700

Data Index: 1892744 (Open Web Text)

Max Activating Token Index: 556