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

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

Neuron 5412 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1226578 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1116815 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3664. Min Act: -0.0000

Data Index: 1169101 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1202441 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3020. Min Act: -0.0000

Data Index: 206521 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3109. Min Act: -0.0000

Data Index: 397375 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.3127. Min Act: -0.0000

Data Index: 440943 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1247863 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.2585. Min Act: -0.0000

Data Index: 405349 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.2650. Min Act: -0.0000

Data Index: 560335 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.2538. Min Act: -0.0000

Data Index: 75165 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.2563. Min Act: -0.0000

Data Index: 1238929 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.2297. Min Act: -0.0000

Data Index: 443566 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.2384. Min Act: -0.0000

Data Index: 699956 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.2453. Min Act: -0.0000

Data Index: 983167 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1039790 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.2304. Min Act: -0.0000

Data Index: 428386 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.2310. Min Act: -0.0000

Data Index: 125026 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.2312. Min Act: -0.0000

Data Index: 488094 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.5860. Min Range: -0.5860

Max Act: 0.2127. Min Act: -0.0000

Data Index: 66879 (C4 (Web Text))

Max Activating Token Index: 643