Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2575 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0294. Min Act: -0.0004

Data Index: 1093089 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0316. Min Act: -0.0004

Data Index: 446582 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0299. Min Act: -0.0004

Data Index: 455643 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0297. Min Act: -0.0004

Data Index: 1607628 (Python Code)

Max Activating Token Index: 52

Text #4

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0287. Min Act: -0.0004

Data Index: 545073 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0274. Min Act: -0.0004

Data Index: 717945 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0292. Min Act: -0.0004

Data Index: 827921 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0281. Min Act: -0.0004

Data Index: 656713 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0281. Min Act: -0.0004

Data Index: 4629 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0274. Min Act: -0.0004

Data Index: 25452 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0277. Min Act: -0.0004

Data Index: 189571 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0274. Min Act: -0.0004

Data Index: 584375 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0264. Min Act: -0.0004

Data Index: 702639 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0283. Min Act: -0.0004

Data Index: 1126975 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0284. Min Act: -0.0004

Data Index: 441367 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0271. Min Act: -0.0004

Data Index: 311974 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0287. Min Act: -0.0004

Data Index: 1176980 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0278. Min Act: -0.0004

Data Index: 275939 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0272. Min Act: -0.0004

Data Index: 769681 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0255. Min Act: -0.0004

Data Index: 1072928 (C4 (Web Text))

Max Activating Token Index: 401