Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 657 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0379. Min Act: -0.0003

Data Index: 214838 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0330. Min Act: -0.0002

Data Index: 593163 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0308. Min Act: -0.0003

Data Index: 843419 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0290. Min Act: -0.0003

Data Index: 1654079 (Python Code)

Max Activating Token Index: 162

Text #4

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1306123 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0288. Min Act: -0.0003

Data Index: 284461 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1629824 (Python Code)

Max Activating Token Index: 151

Text #7

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0275. Min Act: -0.0003

Data Index: 985144 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1006862 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0258. Min Act: -0.0003

Data Index: 468194 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0253. Min Act: -0.0003

Data Index: 657188 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1136016 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0265. Min Act: -0.0003

Data Index: 845440 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0272. Min Act: -0.0003

Data Index: 25721 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0263. Min Act: -0.0003

Data Index: 172980 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0261. Min Act: -0.0003

Data Index: 163663 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0263. Min Act: -0.0003

Data Index: 117681 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1416521 (Python Code)

Max Activating Token Index: 205

Text #18

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0260. Min Act: -0.0003

Data Index: 914079 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0257. Min Act: -0.0003

Data Index: 405003 (C4 (Web Text))

Max Activating Token Index: 490