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

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

Neuron 2194 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: 0.1390. Min Range: -0.1390

Max Act: 0.1365. Min Act: -0.0004

Data Index: 405166 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1336. Min Act: -0.0004

Data Index: 1303525 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1208. Min Act: -0.0004

Data Index: 1327006 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1115. Min Act: -0.0004

Data Index: 332034 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1390. Min Act: -0.0004

Data Index: 595120 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1275. Min Act: -0.0004

Data Index: 223182 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1182. Min Act: -0.0004

Data Index: 784425 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1241. Min Act: -0.0004

Data Index: 1247512 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1251. Min Act: -0.0004

Data Index: 290738 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1276. Min Act: -0.0004

Data Index: 4124 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1142. Min Act: -0.0004

Data Index: 214558 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1230. Min Act: -0.0004

Data Index: 207014 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1168. Min Act: -0.0004

Data Index: 100623 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1219. Min Act: -0.0004

Data Index: 649580 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1154. Min Act: -0.0004

Data Index: 454890 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1345. Min Act: -0.0004

Data Index: 1064583 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1057. Min Act: -0.0004

Data Index: 840678 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1134. Min Act: -0.0004

Data Index: 1065628 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1016. Min Act: -0.0004

Data Index: 318597 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1142. Min Act: -0.0004

Data Index: 929053 (C4 (Web Text))

Max Activating Token Index: 359