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

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

Neuron 3493 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: 0.0314. Min Range: -0.0314

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1111641 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1277508 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1078221 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1217508 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1343213 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0211. Min Act: -0.0003

Data Index: 211745 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0209. Min Act: -0.0003

Data Index: 402495 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0170. Min Act: -0.0003

Data Index: 430425 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1147390 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0203. Min Act: -0.0003

Data Index: 194786 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0194. Min Act: -0.0003

Data Index: 924664 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0190. Min Act: -0.0003

Data Index: 796608 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0189. Min Act: -0.0003

Data Index: 691979 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0194. Min Act: -0.0003

Data Index: 736406 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0195. Min Act: -0.0003

Data Index: 423198 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0190. Min Act: -0.0003

Data Index: 1220200 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0186. Min Act: -0.0003

Data Index: 621968 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1280402 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0172. Min Act: -0.0003

Data Index: 960919 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1147356 (C4 (Web Text))

Max Activating Token Index: 693