Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2748 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0402. Min Act: -0.0001

Data Index: 1640475 (Python Code)

Max Activating Token Index: 96

Text #1

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1592561 (Python Code)

Max Activating Token Index: 935

Text #2

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0340. Min Act: -0.0001

Data Index: 810644 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1316816 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1387904 (Python Code)

Max Activating Token Index: 342

Text #5

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0272. Min Act: -0.0001

Data Index: 424220 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0260. Min Act: -0.0001

Data Index: 204691 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0220. Min Act: -0.0001

Data Index: 155453 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0248. Min Act: -0.0001

Data Index: 445140 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0255. Min Act: -0.0001

Data Index: 1048467 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0246. Min Act: -0.0001

Data Index: 1174236 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0256. Min Act: -0.0001

Data Index: 1572765 (Python Code)

Max Activating Token Index: 720

Text #12

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0267. Min Act: -0.0001

Data Index: 809544 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0236. Min Act: -0.0001

Data Index: 417396 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0263. Min Act: -0.0001

Data Index: 97542 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0235. Min Act: -0.0001

Data Index: 749890 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0210. Min Act: -0.0001

Data Index: 1342312 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1040987 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0230. Min Act: -0.0001

Data Index: 749974 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0237. Min Act: -0.0001

Data Index: 627090 (C4 (Web Text))

Max Activating Token Index: 1013