Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 636 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1525. Min Act: -0.0001

Data Index: 210360 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1357. Min Act: -0.0000

Data Index: 682933 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1352. Min Act: -0.0001

Data Index: 1040953 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1343. Min Act: -0.0002

Data Index: 922886 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1335. Min Act: -0.0002

Data Index: 862321 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1371. Min Act: -0.0001

Data Index: 1327774 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1307. Min Act: -0.0002

Data Index: 955194 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1262. Min Act: -0.0002

Data Index: 1131311 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1295. Min Act: -0.0002

Data Index: 933698 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1192069 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1278. Min Act: -0.0002

Data Index: 638499 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1316. Min Act: -0.0002

Data Index: 32824 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1274. Min Act: -0.0002

Data Index: 1359838 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1204. Min Act: -0.0002

Data Index: 285614 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1250. Min Act: -0.0001

Data Index: 671328 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1246. Min Act: -0.0001

Data Index: 911999 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1207. Min Act: -0.0002

Data Index: 517578 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1223. Min Act: -0.0002

Data Index: 1160142 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1202. Min Act: -0.0001

Data Index: 189944 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1210. Min Act: -0.0002

Data Index: 414877 (C4 (Web Text))

Max Activating Token Index: 535