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

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

Neuron 65 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.4351. Min Act: 0.0000

Data Index: 304917 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.4129. Min Act: -0.0000

Data Index: 1057819 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3526. Min Act: 0.0000

Data Index: 505450 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3612. Min Act: -0.0000

Data Index: 668058 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2953. Min Act: -0.0000

Data Index: 449381 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2950. Min Act: 0.0001

Data Index: 248288 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3052. Min Act: -0.0000

Data Index: 669998 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2915. Min Act: -0.0000

Data Index: 1035123 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3035. Min Act: -0.0000

Data Index: 132777 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2814. Min Act: -0.0000

Data Index: 684159 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2814. Min Act: 0.0000

Data Index: 999453 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2982. Min Act: 0.0000

Data Index: 10940 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2883. Min Act: 0.0000

Data Index: 756325 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2883. Min Act: -0.0000

Data Index: 513517 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2905. Min Act: -0.0000

Data Index: 281688 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1181456 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2799. Min Act: -0.0000

Data Index: 218563 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2615. Min Act: -0.0000

Data Index: 561460 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2726. Min Act: -0.0000

Data Index: 722440 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.2655. Min Act: 0.0000

Data Index: 197407 (C4 (Web Text))

Max Activating Token Index: 809