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

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

Neuron 670 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0002

Data Index: 190285 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0305. Min Act: -0.0002

Data Index: 656444 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0284. Min Act: -0.0002

Data Index: 677834 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0299. Min Act: -0.0002

Data Index: 361057 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0286. Min Act: -0.0002

Data Index: 824875 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0299. Min Act: -0.0002

Data Index: 775961 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0275. Min Act: -0.0002

Data Index: 644974 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0280. Min Act: -0.0002

Data Index: 426608 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0258. Min Act: -0.0002

Data Index: 42294 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0273. Min Act: -0.0002

Data Index: 689182 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0267. Min Act: -0.0002

Data Index: 645837 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0259. Min Act: -0.0002

Data Index: 1461527 (Python Code)

Max Activating Token Index: 50

Text #12

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0265. Min Act: -0.0002

Data Index: 88162 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0261. Min Act: -0.0002

Data Index: 353890 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0248. Min Act: -0.0002

Data Index: 116964 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0253. Min Act: -0.0002

Data Index: 588600 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1552479 (Python Code)

Max Activating Token Index: 38

Text #17

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1116121 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0277. Min Act: -0.0002

Data Index: 776198 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1277124 (C4 (Web Text))

Max Activating Token Index: 392