Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3791 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3237. Min Range: -2.3237

Max Act: 2.3196. Min Act: -0.0000

Data Index: 868742 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 2.3237. Min Range: -2.3237

Max Act: 2.2501. Min Act: -0.0000

Data Index: 440954 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 2.3237. Min Range: -2.3237

Max Act: 2.1224. Min Act: -0.0000

Data Index: 72496 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 2.3237. Min Range: -2.3237

Max Act: 2.3237. Min Act: -0.0000

Data Index: 33268 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 2.3237. Min Range: -2.3237

Max Act: 2.1466. Min Act: -0.0000

Data Index: 65203 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 2.3237. Min Range: -2.3237

Max Act: 2.2303. Min Act: -0.0000

Data Index: 261182 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 2.3237. Min Range: -2.3237

Max Act: 1.9659. Min Act: -0.0000

Data Index: 369193 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 2.3237. Min Range: -2.3237

Max Act: 2.0802. Min Act: -0.0000

Data Index: 1312515 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 2.3237. Min Range: -2.3237

Max Act: 1.9524. Min Act: -0.0000

Data Index: 230991 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 2.3237. Min Range: -2.3237

Max Act: 2.0515. Min Act: -0.0000

Data Index: 390679 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 2.3237. Min Range: -2.3237

Max Act: 2.0288. Min Act: -0.0000

Data Index: 877902 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 2.3237. Min Range: -2.3237

Max Act: 1.9858. Min Act: -0.0000

Data Index: 497644 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 2.3237. Min Range: -2.3237

Max Act: 2.0770. Min Act: -0.0000

Data Index: 156984 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 2.3237. Min Range: -2.3237

Max Act: 1.9728. Min Act: -0.0000

Data Index: 749835 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 2.3237. Min Range: -2.3237

Max Act: 1.9488. Min Act: -0.0000

Data Index: 863376 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 2.3237. Min Range: -2.3237

Max Act: 1.9277. Min Act: -0.0000

Data Index: 14474 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 2.3237. Min Range: -2.3237

Max Act: 1.9196. Min Act: -0.0000

Data Index: 460259 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 2.3237. Min Range: -2.3237

Max Act: 1.8941. Min Act: -0.0000

Data Index: 1322371 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 2.3237. Min Range: -2.3237

Max Act: 1.7869. Min Act: -0.0000

Data Index: 1233881 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 2.3237. Min Range: -2.3237

Max Act: 1.8962. Min Act: -0.0000

Data Index: 1347394 (C4 (Web Text))

Max Activating Token Index: 831