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

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

Neuron 4619 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: 0.0326. Min Range: -0.0326

Max Act: 0.0326. Min Act: -0.0003

Data Index: 243789 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0322. Min Act: -0.0002

Data Index: 303190 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1239216 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0294. Min Act: -0.0003

Data Index: 126546 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1133036 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0304. Min Act: -0.0003

Data Index: 989079 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0270. Min Act: -0.0003

Data Index: 512583 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0278. Min Act: -0.0003

Data Index: 3188 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0267. Min Act: -0.0003

Data Index: 924663 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0256. Min Act: -0.0003

Data Index: 448134 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1309313 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0257. Min Act: -0.0002

Data Index: 707462 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0237. Min Act: -0.0003

Data Index: 956808 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0242. Min Act: -0.0002

Data Index: 406679 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0243. Min Act: -0.0003

Data Index: 990060 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0254. Min Act: -0.0003

Data Index: 692355 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0255. Min Act: -0.0002

Data Index: 688158 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0242. Min Act: -0.0002

Data Index: 823081 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0258. Min Act: -0.0003

Data Index: 996153 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0257. Min Act: -0.0003

Data Index: 255352 (C4 (Web Text))

Max Activating Token Index: 113