Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3164 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0578. Min Act: -0.0003

Data Index: 1612063 (Python Code)

Max Activating Token Index: 178

Text #1

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0549. Min Act: -0.0003

Data Index: 662244 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0500. Min Act: -0.0004

Data Index: 1344876 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0435. Min Act: -0.0003

Data Index: 894708 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0389. Min Act: -0.0003

Data Index: 161601 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1481300 (Python Code)

Max Activating Token Index: 547

Text #6

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0341. Min Act: -0.0003

Data Index: 869552 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1083316 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0324. Min Act: -0.0003

Data Index: 637415 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0311. Min Act: -0.0003

Data Index: 377532 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0346. Min Act: -0.0003

Data Index: 933460 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0344. Min Act: -0.0003

Data Index: 712297 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0323. Min Act: -0.0003

Data Index: 348755 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0323. Min Act: -0.0003

Data Index: 554378 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1034756 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1218039 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0372. Min Act: -0.0003

Data Index: 634527 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1241419 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0314. Min Act: -0.0004

Data Index: 152095 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.0578. Min Range: -0.0578

Max Act: 0.0330. Min Act: -0.0003

Data Index: 185272 (C4 (Web Text))

Max Activating Token Index: 479