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

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

Neuron 1536 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0532. Min Act: -0.0002

Data Index: 455728 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1087600 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0471. Min Act: -0.0002

Data Index: 570373 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0414. Min Act: -0.0002

Data Index: 482185 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0411. Min Act: -0.0002

Data Index: 228837 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0396. Min Act: -0.0002

Data Index: 472740 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0383. Min Act: -0.0002

Data Index: 463807 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1150318 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0371. Min Act: -0.0002

Data Index: 775774 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0352. Min Act: -0.0002

Data Index: 719749 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0389. Min Act: -0.0002

Data Index: 922690 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0357. Min Act: -0.0002

Data Index: 910294 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0341. Min Act: -0.0002

Data Index: 24049 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1350004 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0356. Min Act: -0.0002

Data Index: 933734 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0360. Min Act: -0.0002

Data Index: 758209 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1253245 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0327. Min Act: -0.0002

Data Index: 534330 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0356. Min Act: -0.0002

Data Index: 347547 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0343. Min Act: -0.0002

Data Index: 899364 (C4 (Web Text))

Max Activating Token Index: 778