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

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

Neuron 4948 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: 0.0805. Min Range: -0.0805

Max Act: 0.0805. Min Act: -0.0002

Data Index: 584939 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0538. Min Act: -0.0002

Data Index: 797807 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0539. Min Act: -0.0002

Data Index: 393701 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0571. Min Act: -0.0002

Data Index: 61709 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0543. Min Act: -0.0002

Data Index: 451819 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1506910 (Python Code)

Max Activating Token Index: 121

Text #6

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0484. Min Act: -0.0002

Data Index: 164051 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0453. Min Act: -0.0002

Data Index: 782128 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1058258 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0522. Min Act: -0.0002

Data Index: 547032 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0474. Min Act: -0.0002

Data Index: 485093 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1023981 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1032744 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0355. Min Act: -0.0002

Data Index: 162049 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1522928 (Python Code)

Max Activating Token Index: 904

Text #15

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0575. Min Act: -0.0002

Data Index: 825481 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1036734 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0423. Min Act: -0.0002

Data Index: 938833 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1355033 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.0805. Min Range: -0.0805

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1116682 (C4 (Web Text))

Max Activating Token Index: 775