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

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

Neuron 577 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1176881 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0204. Min Act: -0.0002

Data Index: 458713 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0212. Min Act: -0.0002

Data Index: 983112 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0197. Min Act: -0.0002

Data Index: 1139128 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0188. Min Act: -0.0002

Data Index: 63557 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0183. Min Act: -0.0002

Data Index: 1078545 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1595419 (Python Code)

Max Activating Token Index: 626

Text #7

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1415911 (Python Code)

Max Activating Token Index: 869

Text #8

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0171. Min Act: -0.0003

Data Index: 67451 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1566360 (Python Code)

Max Activating Token Index: 433

Text #10

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1259380 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1134643 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0186. Min Act: -0.0002

Data Index: 293333 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0172. Min Act: -0.0002

Data Index: 927933 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1535778 (Python Code)

Max Activating Token Index: 517

Text #15

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1089971 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1184835 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0167. Min Act: -0.0002

Data Index: 1574678 (Python Code)

Max Activating Token Index: 130

Text #18

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1628693 (Python Code)

Max Activating Token Index: 748

Text #19

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0158. Min Act: -0.0002

Data Index: 521788 (C4 (Web Text))

Max Activating Token Index: 415