Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1708 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.5868. Min Act: -0.0000

Data Index: 41211 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.5637. Min Act: -0.0000

Data Index: 892298 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1275550 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.5192. Min Act: -0.0000

Data Index: 574731 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1051553 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4611. Min Act: -0.0000

Data Index: 291395 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4734. Min Act: -0.0000

Data Index: 400973 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.5058. Min Act: -0.0000

Data Index: 351460 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4491. Min Act: -0.0000

Data Index: 105698 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4160. Min Act: -0.0000

Data Index: 973603 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4513. Min Act: -0.0000

Data Index: 289937 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4008. Min Act: -0.0000

Data Index: 224975 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4259. Min Act: -0.0000

Data Index: 188631 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4665. Min Act: -0.0000

Data Index: 639106 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1079976 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4292. Min Act: -0.0000

Data Index: 897759 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4249. Min Act: -0.0000

Data Index: 627319 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1121347 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1137644 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.5868. Min Range: -0.5868

Max Act: 0.3416. Min Act: -0.0000

Data Index: 403270 (C4 (Web Text))

Max Activating Token Index: 450