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

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

Neuron 4099 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0267. Min Act: -0.0001

Data Index: 567153 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0251. Min Act: -0.0001

Data Index: 1251843 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0292. Min Act: -0.0001

Data Index: 311866 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0255. Min Act: -0.0001

Data Index: 611280 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1180635 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0237. Min Act: -0.0001

Data Index: 717237 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0195. Min Act: -0.0001

Data Index: 1595979 (Python Code)

Max Activating Token Index: 373

Text #7

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0174. Min Act: -0.0001

Data Index: 1566395 (Python Code)

Max Activating Token Index: 426

Text #8

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0194. Min Act: -0.0001

Data Index: 486528 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0186. Min Act: -0.0001

Data Index: 1270400 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0156. Min Act: -0.0001

Data Index: 995699 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0179. Min Act: -0.0001

Data Index: 40855 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0156. Min Act: -0.0001

Data Index: 216301 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0151. Min Act: -0.0001

Data Index: 1327686 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0152. Min Act: -0.0001

Data Index: 459341 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0157. Min Act: -0.0001

Data Index: 1346261 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0173. Min Act: -0.0001

Data Index: 411816 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0159. Min Act: -0.0001

Data Index: 1603208 (Python Code)

Max Activating Token Index: 374

Text #18

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0145. Min Act: -0.0001

Data Index: 402197 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0147. Min Act: -0.0001

Data Index: 189018 (C4 (Web Text))

Max Activating Token Index: 546