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

Dataset: The Pile

Neuron 2498 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8897. Min Act: -0.0000

Data Index: 585503 (The Pile)

Max Activating Token Index: 230

Text #1

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1961480 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1280697 (The Pile)

Max Activating Token Index: 634

Text #3

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8887. Min Act: -0.0000

Data Index: 562345 (The Pile)

Max Activating Token Index: 38

Text #4

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8646. Min Act: -0.0000

Data Index: 1917496 (The Pile)

Max Activating Token Index: 541

Text #5

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1794987 (The Pile)

Max Activating Token Index: 353

Text #6

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1369215 (The Pile)

Max Activating Token Index: 237

Text #7

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1323180 (The Pile)

Max Activating Token Index: 157

Text #8

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7828. Min Act: -0.0000

Data Index: 1659821 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1438404 (The Pile)

Max Activating Token Index: 608

Text #10

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7822. Min Act: -0.0000

Data Index: 562460 (The Pile)

Max Activating Token Index: 962

Text #11

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7734. Min Act: -0.0000

Data Index: 865312 (The Pile)

Max Activating Token Index: 281

Text #12

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7383. Min Act: -0.0000

Data Index: 1050534 (The Pile)

Max Activating Token Index: 181

Text #13

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1880505 (The Pile)

Max Activating Token Index: 580

Text #14

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7254. Min Act: -0.0000

Data Index: 1514318 (The Pile)

Max Activating Token Index: 403

Text #15

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7730. Min Act: -0.0000

Data Index: 1329108 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7155. Min Act: -0.0000

Data Index: 103685 (The Pile)

Max Activating Token Index: 246

Text #17

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7478. Min Act: -0.0000

Data Index: 737855 (The Pile)

Max Activating Token Index: 868

Text #18

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1860290 (The Pile)

Max Activating Token Index: 204

Text #19

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7413. Min Act: -0.0000

Data Index: 601780 (The Pile)

Max Activating Token Index: 349