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

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

Neuron 226 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: 0.0334. Min Range: -0.0334

Max Act: 0.0334. Min Act: -0.0002

Data Index: 923477 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0306. Min Act: -0.0002

Data Index: 284028 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0296. Min Act: -0.0002

Data Index: 950447 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0272. Min Act: -0.0002

Data Index: 392832 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0269. Min Act: -0.0002

Data Index: 18904 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0266. Min Act: -0.0002

Data Index: 673655 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0266. Min Act: -0.0002

Data Index: 794293 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1373576 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0262. Min Act: -0.0002

Data Index: 694376 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0255. Min Act: -0.0002

Data Index: 534550 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0260. Min Act: -0.0002

Data Index: 611429 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0260. Min Act: -0.0002

Data Index: 153321 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1096208 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0257. Min Act: -0.0002

Data Index: 73108 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0256. Min Act: -0.0002

Data Index: 98724 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1054302 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0249. Min Act: -0.0002

Data Index: 839630 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0254. Min Act: -0.0002

Data Index: 1403243 (Python Code)

Max Activating Token Index: 161

Text #18

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1282104 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1325834 (C4 (Web Text))

Max Activating Token Index: 786