Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3676 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0001

Data Index: 310104 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0301. Min Act: -0.0001

Data Index: 786737 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0309. Min Act: -0.0000

Data Index: 19058 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1655256 (Python Code)

Max Activating Token Index: 797

Text #4

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1433834 (Python Code)

Max Activating Token Index: 513

Text #5

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0276. Min Act: -0.0001

Data Index: 1585477 (Python Code)

Max Activating Token Index: 339

Text #6

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0271. Min Act: -0.0001

Data Index: 1539734 (Python Code)

Max Activating Token Index: 726

Text #7

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0259. Min Act: -0.0001

Data Index: 1095603 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0272. Min Act: -0.0001

Data Index: 1271413 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0268. Min Act: -0.0000

Data Index: 1469537 (Python Code)

Max Activating Token Index: 186

Text #10

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0248. Min Act: -0.0001

Data Index: 487911 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0254. Min Act: 0.0001

Data Index: 374033 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0252. Min Act: -0.0001

Data Index: 1170283 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0245. Min Act: -0.0000

Data Index: 1383449 (Python Code)

Max Activating Token Index: 428

Text #14

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0247. Min Act: 0.0001

Data Index: 86405 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0252. Min Act: -0.0001

Data Index: 1635716 (Python Code)

Max Activating Token Index: 370

Text #16

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0236. Min Act: -0.0001

Data Index: 715169 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0252. Min Act: -0.0000

Data Index: 985974 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0242. Min Act: 0.0002

Data Index: 1149275 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0231. Min Act: -0.0001

Data Index: 844628 (C4 (Web Text))

Max Activating Token Index: 963