Model: GELU Model: 2 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 438 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.6082. Min Range: -5.6082

Max Act: 5.6082. Min Act: -0.1700

Data Index: 987461 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 5.6082. Min Range: -5.6082

Max Act: 5.0457. Min Act: -0.1700

Data Index: 1213782 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 5.6082. Min Range: -5.6082

Max Act: 5.1082. Min Act: -0.1700

Data Index: 766871 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 5.6082. Min Range: -5.6082

Max Act: 5.0769. Min Act: -0.1700

Data Index: 226085 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 5.6082. Min Range: -5.6082

Max Act: 5.0144. Min Act: -0.1700

Data Index: 1063541 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 5.6082. Min Range: -5.6082

Max Act: 5.0457. Min Act: -0.1700

Data Index: 87283 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 5.6082. Min Range: -5.6082

Max Act: 5.0457. Min Act: -0.1700

Data Index: 954652 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 5.6082. Min Range: -5.6082

Max Act: 4.9832. Min Act: -0.1700

Data Index: 1231225 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 5.6082. Min Range: -5.6082

Max Act: 4.9832. Min Act: -0.1700

Data Index: 1177023 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 5.6082. Min Range: -5.6082

Max Act: 5.0144. Min Act: -0.1700

Data Index: 793391 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 5.6082. Min Range: -5.6082

Max Act: 4.9832. Min Act: -0.1700

Data Index: 230601 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 5.6082. Min Range: -5.6082

Max Act: 4.9519. Min Act: -0.1700

Data Index: 658066 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 5.6082. Min Range: -5.6082

Max Act: 4.9207. Min Act: -0.1700

Data Index: 85561 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 5.6082. Min Range: -5.6082

Max Act: 4.9207. Min Act: -0.1700

Data Index: 898288 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 5.6082. Min Range: -5.6082

Max Act: 4.9519. Min Act: -0.1700

Data Index: 1094077 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 5.6082. Min Range: -5.6082

Max Act: 4.9519. Min Act: -0.1700

Data Index: 89910 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 5.6082. Min Range: -5.6082

Max Act: 4.9519. Min Act: -0.1700

Data Index: 4187 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 5.6082. Min Range: -5.6082

Max Act: 4.8894. Min Act: -0.1700

Data Index: 795076 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 5.6082. Min Range: -5.6082

Max Act: 4.9207. Min Act: -0.1700

Data Index: 727061 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 5.6082. Min Range: -5.6082

Max Act: 4.9519. Min Act: -0.1700

Data Index: 115683 (C4 (Web Text))

Max Activating Token Index: 791