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

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

Neuron 1187 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: 0.7787. Min Range: -0.7787

Max Act: 0.7787. Min Act: -0.0000

Data Index: 966853 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.7170. Min Act: -0.0000

Data Index: 652689 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1008382 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.7281. Min Act: -0.0000

Data Index: 290483 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1010493 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.7033. Min Act: -0.0000

Data Index: 1319582 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6763. Min Act: -0.0000

Data Index: 122723 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6938. Min Act: -0.0000

Data Index: 614198 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6869. Min Act: -0.0000

Data Index: 931427 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6244. Min Act: -0.0000

Data Index: 465700 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6599. Min Act: -0.0000

Data Index: 233903 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6517. Min Act: -0.0000

Data Index: 113583 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6275. Min Act: -0.0000

Data Index: 628664 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1335774 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6418. Min Act: -0.0000

Data Index: 623664 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6272. Min Act: -0.0000

Data Index: 1020522 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6405. Min Act: -0.0000

Data Index: 808657 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6141. Min Act: -0.0000

Data Index: 681646 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.5934. Min Act: -0.0000

Data Index: 765456 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6380. Min Act: -0.0000

Data Index: 488673 (C4 (Web Text))

Max Activating Token Index: 315