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

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

Neuron 1092 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0267. Min Act: -0.0002

Data Index: 310077 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0262. Min Act: -0.0002

Data Index: 640116 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1129747 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0242. Min Act: -0.0002

Data Index: 123990 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0240. Min Act: -0.0002

Data Index: 56480 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0235. Min Act: -0.0002

Data Index: 935819 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0234. Min Act: -0.0002

Data Index: 334099 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0234. Min Act: -0.0002

Data Index: 473405 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1322430 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0226. Min Act: -0.0002

Data Index: 803663 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0229. Min Act: -0.0002

Data Index: 144514 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0226. Min Act: -0.0002

Data Index: 526016 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0225. Min Act: -0.0002

Data Index: 254300 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0218. Min Act: -0.0002

Data Index: 751242 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1249110 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0221. Min Act: -0.0002

Data Index: 1543302 (Python Code)

Max Activating Token Index: 127

Text #16

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0224. Min Act: -0.0002

Data Index: 769579 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0220. Min Act: -0.0002

Data Index: 159621 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0220. Min Act: -0.0002

Data Index: 61534 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0219. Min Act: -0.0002

Data Index: 345490 (C4 (Web Text))

Max Activating Token Index: 17