Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4059 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0374. Min Act: -0.0002

Data Index: 638322 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1059419 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0300. Min Act: -0.0002

Data Index: 249942 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0290. Min Act: -0.0002

Data Index: 979331 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1645840 (Python Code)

Max Activating Token Index: 187

Text #5

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0284. Min Act: -0.0002

Data Index: 442098 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0285. Min Act: -0.0002

Data Index: 151 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1235508 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0279. Min Act: -0.0002

Data Index: 107616 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0276. Min Act: -0.0002

Data Index: 747705 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1048554 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0268. Min Act: -0.0002

Data Index: 267917 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0259. Min Act: -0.0002

Data Index: 612393 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0258. Min Act: -0.0002

Data Index: 389257 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0257. Min Act: -0.0002

Data Index: 775527 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0254. Min Act: -0.0002

Data Index: 36947 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0251. Min Act: -0.0002

Data Index: 991297 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0248. Min Act: -0.0002

Data Index: 368997 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1034402 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0237. Min Act: -0.0002

Data Index: 100295 (C4 (Web Text))

Max Activating Token Index: 812