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

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

Neuron 655 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: 0.0391. Min Range: -0.0391

Max Act: 0.0391. Min Act: -0.0002

Data Index: 705792 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0324. Min Act: -0.0003

Data Index: 688599 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0290. Min Act: -0.0002

Data Index: 764352 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0296. Min Act: -0.0003

Data Index: 493027 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0276. Min Act: -0.0003

Data Index: 157243 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0289. Min Act: -0.0003

Data Index: 1330083 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0278. Min Act: -0.0003

Data Index: 1374572 (Python Code)

Max Activating Token Index: 84

Text #7

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0261. Min Act: -0.0003

Data Index: 924802 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0272. Min Act: -0.0003

Data Index: 764237 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0261. Min Act: -0.0002

Data Index: 484237 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1300983 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1091156 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1164904 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0263. Min Act: -0.0003

Data Index: 463767 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0262. Min Act: -0.0003

Data Index: 94831 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1491527 (Python Code)

Max Activating Token Index: 795

Text #16

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0261. Min Act: -0.0003

Data Index: 674893 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0262. Min Act: -0.0003

Data Index: 437554 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1369209 (Python Code)

Max Activating Token Index: 172

Text #19

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0260. Min Act: -0.0003

Data Index: 95845 (C4 (Web Text))

Max Activating Token Index: 673