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

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

Neuron 2674 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: 0.0320. Min Range: -0.0320

Max Act: 0.0320. Min Act: -0.0003

Data Index: 843283 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0261. Min Act: -0.0003

Data Index: 866071 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0239. Min Act: -0.0003

Data Index: 985648 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0214. Min Act: -0.0003

Data Index: 650669 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1182554 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0245. Min Act: -0.0003

Data Index: 45703 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1218074 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0203. Min Act: -0.0003

Data Index: 369587 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0210. Min Act: -0.0003

Data Index: 1228052 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0205. Min Act: -0.0003

Data Index: 513676 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0225. Min Act: -0.0004

Data Index: 817204 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0201. Min Act: -0.0003

Data Index: 884461 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1175999 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0203. Min Act: -0.0003

Data Index: 1007198 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0212. Min Act: -0.0003

Data Index: 8149 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0186. Min Act: -0.0003

Data Index: 1260961 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0221. Min Act: -0.0003

Data Index: 708223 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0182. Min Act: -0.0003

Data Index: 1389319 (Python Code)

Max Activating Token Index: 105

Text #18

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1346056 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0198. Min Act: -0.0003

Data Index: 251417 (C4 (Web Text))

Max Activating Token Index: 179