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

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

Neuron 3467 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.4044. Min Act: -0.0001

Data Index: 1143063 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.3478. Min Act: -0.0001

Data Index: 438423 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.3471. Min Act: -0.0000

Data Index: 298032 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.3538. Min Act: -0.0001

Data Index: 485988 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.3119. Min Act: -0.0001

Data Index: 1285433 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.3411. Min Act: -0.0001

Data Index: 627734 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.3169. Min Act: -0.0001

Data Index: 1246548 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.3098. Min Act: -0.0001

Data Index: 1034649 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.2943. Min Act: -0.0001

Data Index: 247496 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.3081. Min Act: -0.0001

Data Index: 402792 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.3107. Min Act: -0.0000

Data Index: 612964 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.2912. Min Act: -0.0001

Data Index: 65473 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.2843. Min Act: -0.0001

Data Index: 340808 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.2714. Min Act: -0.0001

Data Index: 231704 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.2912. Min Act: -0.0001

Data Index: 1040647 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.2546. Min Act: -0.0001

Data Index: 909361 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.2793. Min Act: -0.0001

Data Index: 244215 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.2453. Min Act: -0.0001

Data Index: 681842 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.2702. Min Act: -0.0001

Data Index: 367422 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.4044. Min Range: -0.4044

Max Act: 0.2616. Min Act: -0.0001

Data Index: 1351780 (C4 (Web Text))

Max Activating Token Index: 355