Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 19 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0411. Min Act: -0.0001

Data Index: 181127 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1074136 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0373. Min Act: -0.0001

Data Index: 1034118 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1000585 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0329. Min Act: -0.0001

Data Index: 28575 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0325. Min Act: -0.0001

Data Index: 33625 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0356. Min Act: -0.0001

Data Index: 526296 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0326. Min Act: -0.0001

Data Index: 663979 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0328. Min Act: -0.0001

Data Index: 811095 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0312. Min Act: -0.0001

Data Index: 140815 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0322. Min Act: -0.0001

Data Index: 145387 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0278. Min Act: -0.0001

Data Index: 396158 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0286. Min Act: -0.0001

Data Index: 1079604 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0274. Min Act: -0.0001

Data Index: 119431 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0293. Min Act: -0.0001

Data Index: 265448 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0274. Min Act: -0.0001

Data Index: 138125 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0281. Min Act: -0.0001

Data Index: 444776 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0280. Min Act: -0.0001

Data Index: 624819 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0280. Min Act: -0.0001

Data Index: 43716 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.0411. Min Range: -0.0411

Max Act: 0.0268. Min Act: -0.0001

Data Index: 52176 (C4 (Web Text))

Max Activating Token Index: 1015