Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2466 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0375. Min Act: -0.0004

Data Index: 1216030 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0363. Min Act: -0.0004

Data Index: 1291045 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0311. Min Act: -0.0004

Data Index: 935817 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0311. Min Act: -0.0004

Data Index: 623170 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0286. Min Act: -0.0004

Data Index: 1114961 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0245. Min Act: -0.0004

Data Index: 653861 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0244. Min Act: -0.0004

Data Index: 940279 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0251. Min Act: -0.0004

Data Index: 584536 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0249. Min Act: -0.0004

Data Index: 611597 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0240. Min Act: -0.0004

Data Index: 1130191 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0236. Min Act: -0.0004

Data Index: 429422 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0260. Min Act: -0.0004

Data Index: 1027664 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0208. Min Act: -0.0004

Data Index: 1270579 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0218. Min Act: -0.0004

Data Index: 135287 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0230. Min Act: -0.0004

Data Index: 222353 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0200. Min Act: -0.0004

Data Index: 49714 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0222. Min Act: -0.0004

Data Index: 1046574 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0222. Min Act: -0.0004

Data Index: 311652 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0216. Min Act: -0.0004

Data Index: 1028457 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0225. Min Act: -0.0004

Data Index: 1106795 (C4 (Web Text))

Max Activating Token Index: 723