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

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

Neuron 4735 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0462. Min Act: -0.0002

Data Index: 30873 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1000257 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1101736 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1171355 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1002658 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0390. Min Act: -0.0002

Data Index: 64066 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1171417 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0344. Min Act: -0.0002

Data Index: 558778 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0346. Min Act: -0.0002

Data Index: 783910 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0347. Min Act: -0.0002

Data Index: 52960 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0340. Min Act: -0.0002

Data Index: 49589 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1341778 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0345. Min Act: -0.0002

Data Index: 162350 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0341. Min Act: -0.0002

Data Index: 181502 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0369. Min Act: -0.0002

Data Index: 608613 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0322. Min Act: -0.0002

Data Index: 388244 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1070895 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0331. Min Act: -0.0002

Data Index: 889496 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0319. Min Act: -0.0002

Data Index: 654536 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.0462. Min Range: -0.0462

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1537018 (Python Code)

Max Activating Token Index: 58