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

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

Neuron 2808 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0210. Min Act: -0.0003

Data Index: 1367899 (Python Code)

Max Activating Token Index: 146

Text #1

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0213. Min Act: -0.0003

Data Index: 1616086 (Python Code)

Max Activating Token Index: 371

Text #2

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0194. Min Act: -0.0003

Data Index: 1460511 (Python Code)

Max Activating Token Index: 341

Text #3

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0194. Min Act: -0.0003

Data Index: 393065 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0193. Min Act: -0.0003

Data Index: 238779 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0197. Min Act: -0.0003

Data Index: 131244 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0194. Min Act: -0.0003

Data Index: 574415 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1495602 (Python Code)

Max Activating Token Index: 315

Text #8

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0196. Min Act: -0.0004

Data Index: 1493958 (Python Code)

Max Activating Token Index: 557

Text #9

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0186. Min Act: -0.0003

Data Index: 1551801 (Python Code)

Max Activating Token Index: 322

Text #10

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0147. Min Act: -0.0003

Data Index: 1357653 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1413673 (Python Code)

Max Activating Token Index: 529

Text #12

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0183. Min Act: -0.0003

Data Index: 508811 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1552879 (Python Code)

Max Activating Token Index: 462

Text #14

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0178. Min Act: -0.0003

Data Index: 1559099 (Python Code)

Max Activating Token Index: 430

Text #15

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0185. Min Act: -0.0004

Data Index: 1351599 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0177. Min Act: -0.0003

Data Index: 1602261 (Python Code)

Max Activating Token Index: 947

Text #17

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0188. Min Act: -0.0003

Data Index: 509212 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1649285 (Python Code)

Max Activating Token Index: 529

Text #19

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1604653 (Python Code)

Max Activating Token Index: 592