Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1416 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0303. Min Act: -0.0006

Data Index: 1256741 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1076987 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0242. Min Act: -0.0006

Data Index: 1260087 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0252. Min Act: -0.0006

Data Index: 1158322 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0251. Min Act: -0.0006

Data Index: 841235 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0247. Min Act: -0.0006

Data Index: 177417 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1154451 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1039032 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0227. Min Act: -0.0006

Data Index: 851968 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1184538 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0239. Min Act: -0.0006

Data Index: 976982 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0231. Min Act: -0.0006

Data Index: 169653 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0234. Min Act: -0.0006

Data Index: 14890 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1238269 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0242. Min Act: -0.0006

Data Index: 829698 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0221. Min Act: -0.0006

Data Index: 777446 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0216. Min Act: -0.0006

Data Index: 338068 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0225. Min Act: -0.0006

Data Index: 1075128 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0228. Min Act: -0.0006

Data Index: 1290815 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1001000 (C4 (Web Text))

Max Activating Token Index: 993