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

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

Neuron 3745 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.6228. Min Act: -0.0001

Data Index: 104456 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5615. Min Act: -0.0001

Data Index: 1006038 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5462. Min Act: -0.0001

Data Index: 1241609 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5575. Min Act: -0.0001

Data Index: 1122703 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5567. Min Act: -0.0001

Data Index: 83924 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5703. Min Act: -0.0001

Data Index: 1338567 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5478. Min Act: -0.0001

Data Index: 240226 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5495. Min Act: -0.0001

Data Index: 1333205 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5454. Min Act: -0.0001

Data Index: 672266 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5238. Min Act: -0.0001

Data Index: 1068260 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5190. Min Act: -0.0001

Data Index: 539282 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5314. Min Act: -0.0001

Data Index: 50226 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5255. Min Act: -0.0001

Data Index: 145735 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5270. Min Act: -0.0001

Data Index: 735719 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5085. Min Act: -0.0001

Data Index: 332687 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5241. Min Act: -0.0001

Data Index: 741582 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5411. Min Act: -0.0001

Data Index: 1027998 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5180. Min Act: -0.0001

Data Index: 799812 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5184. Min Act: -0.0001

Data Index: 713627 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.6228. Min Range: -0.6228

Max Act: 0.5350. Min Act: -0.0001

Data Index: 1009336 (C4 (Web Text))

Max Activating Token Index: 304