Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1045 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1611162 (Python Code)

Max Activating Token Index: 406

Text #1

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1012968 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0241. Min Act: -0.0003

Data Index: 685043 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1363424 (Python Code)

Max Activating Token Index: 850

Text #4

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1527503 (Python Code)

Max Activating Token Index: 647

Text #5

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0235. Min Act: -0.0003

Data Index: 430272 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1144529 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1308184 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1470023 (Python Code)

Max Activating Token Index: 708

Text #9

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0233. Min Act: -0.0003

Data Index: 101960 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1629745 (Python Code)

Max Activating Token Index: 958

Text #11

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1590851 (Python Code)

Max Activating Token Index: 541

Text #12

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0229. Min Act: -0.0003

Data Index: 1440171 (Python Code)

Max Activating Token Index: 176

Text #13

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1616545 (Python Code)

Max Activating Token Index: 236

Text #14

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0224. Min Act: -0.0003

Data Index: 1640505 (Python Code)

Max Activating Token Index: 190

Text #15

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0226. Min Act: -0.0003

Data Index: 172333 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0222. Min Act: -0.0003

Data Index: 863138 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0220. Min Act: -0.0003

Data Index: 766943 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0218. Min Act: -0.0003

Data Index: 473567 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0214. Min Act: -0.0003

Data Index: 942559 (C4 (Web Text))

Max Activating Token Index: 166