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

Dataset: The Pile

Neuron 4601 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.8471. Min Act: -0.0000

Data Index: 858697 (The Pile)

Max Activating Token Index: 579

Text #1

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.8711. Min Act: 0.0000

Data Index: 1523399 (The Pile)

Max Activating Token Index: 201

Text #2

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7047. Min Act: -0.0000

Data Index: 934502 (The Pile)

Max Activating Token Index: 206

Text #3

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1137466 (The Pile)

Max Activating Token Index: 890

Text #4

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7182. Min Act: 0.0000

Data Index: 1425402 (The Pile)

Max Activating Token Index: 557

Text #5

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1858912 (The Pile)

Max Activating Token Index: 205

Text #6

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1078884 (The Pile)

Max Activating Token Index: 643

Text #7

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1279897 (The Pile)

Max Activating Token Index: 778

Text #8

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6731. Min Act: 0.0000

Data Index: 1500429 (The Pile)

Max Activating Token Index: 87

Text #9

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6238. Min Act: 0.0000

Data Index: 89919 (The Pile)

Max Activating Token Index: 746

Text #10

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6677. Min Act: -0.0000

Data Index: 412686 (The Pile)

Max Activating Token Index: 353

Text #11

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6624. Min Act: -0.0000

Data Index: 387576 (The Pile)

Max Activating Token Index: 749

Text #12

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6449. Min Act: 0.0000

Data Index: 1827652 (The Pile)

Max Activating Token Index: 450

Text #13

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1144101 (The Pile)

Max Activating Token Index: 295

Text #14

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1053114 (The Pile)

Max Activating Token Index: 30

Text #15

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6506. Min Act: -0.0000

Data Index: 959329 (The Pile)

Max Activating Token Index: 716

Text #16

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1733617 (The Pile)

Max Activating Token Index: 423

Text #17

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.5946. Min Act: -0.0000

Data Index: 286443 (The Pile)

Max Activating Token Index: 360

Text #18

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1449690 (The Pile)

Max Activating Token Index: 899

Text #19

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6644. Min Act: -0.0000

Data Index: 42832 (The Pile)

Max Activating Token Index: 484