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

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

Neuron 3286 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0417. Min Act: -0.0003

Data Index: 176481 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1094195 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0332. Min Act: -0.0003

Data Index: 618602 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0372. Min Act: -0.0003

Data Index: 295577 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0316. Min Act: -0.0003

Data Index: 780157 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1118014 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1190724 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0260. Min Act: -0.0003

Data Index: 127319 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0297. Min Act: -0.0003

Data Index: 171037 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1209452 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1318679 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0313. Min Act: -0.0003

Data Index: 219957 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1068766 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0314. Min Act: -0.0003

Data Index: 559457 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0272. Min Act: -0.0002

Data Index: 888905 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0283. Min Act: -0.0003

Data Index: 288768 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0305. Min Act: -0.0003

Data Index: 446587 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0307. Min Act: -0.0003

Data Index: 873921 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0300. Min Act: -0.0003

Data Index: 980079 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0301. Min Act: -0.0002

Data Index: 489560 (C4 (Web Text))

Max Activating Token Index: 661