Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 160 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0405. Min Act: -0.0000

Data Index: 1029955 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0309. Min Act: -0.0000

Data Index: 38811 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0328. Min Act: -0.0000

Data Index: 909451 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0290. Min Act: -0.0000

Data Index: 1474267 (Python Code)

Max Activating Token Index: 459

Text #4

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0290. Min Act: -0.0000

Data Index: 553656 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0290. Min Act: -0.0000

Data Index: 515993 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0279. Min Act: -0.0000

Data Index: 884718 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0275. Min Act: -0.0000

Data Index: 344841 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0274. Min Act: -0.0000

Data Index: 945765 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0261. Min Act: -0.0000

Data Index: 724858 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0266. Min Act: -0.0000

Data Index: 950289 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0245. Min Act: -0.0000

Data Index: 1155213 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0242. Min Act: -0.0000

Data Index: 1487383 (Python Code)

Max Activating Token Index: 145

Text #13

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0249. Min Act: -0.0000

Data Index: 162798 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0255. Min Act: -0.0000

Data Index: 97613 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0236. Min Act: -0.0000

Data Index: 645120 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0251. Min Act: -0.0000

Data Index: 899555 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0231. Min Act: -0.0000

Data Index: 522827 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0229. Min Act: -0.0000

Data Index: 1342500 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0228. Min Act: -0.0000

Data Index: 1185457 (C4 (Web Text))

Max Activating Token Index: 536