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

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

Neuron 3965 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: 1.3298. Min Range: -1.3298

Max Act: 1.3298. Min Act: -0.0003

Data Index: 164333 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.2201. Min Act: -0.0003

Data Index: 953165 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.2476. Min Act: -0.0003

Data Index: 83481 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.1177. Min Act: -0.0003

Data Index: 479114 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.1093. Min Act: -0.0003

Data Index: 1351264 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.0382. Min Act: -0.0003

Data Index: 401223 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.0646. Min Act: -0.0003

Data Index: 1234840 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.0376. Min Act: -0.0003

Data Index: 304213 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9740. Min Act: -0.0003

Data Index: 457 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.0216. Min Act: -0.0003

Data Index: 628377 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 1.3298. Min Range: -1.3298

Max Act: 1.0166. Min Act: -0.0003

Data Index: 23679 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9885. Min Act: -0.0003

Data Index: 1208810 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9809. Min Act: -0.0002

Data Index: 507663 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9695. Min Act: -0.0003

Data Index: 581418 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9487. Min Act: -0.0003

Data Index: 1027300 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9360. Min Act: -0.0003

Data Index: 998594 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9543. Min Act: -0.0003

Data Index: 284193 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.9245. Min Act: -0.0003

Data Index: 1220166 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.8808. Min Act: -0.0003

Data Index: 1327010 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 1.3298. Min Range: -1.3298

Max Act: 0.8661. Min Act: -0.0003

Data Index: 648172 (C4 (Web Text))

Max Activating Token Index: 289