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

Dataset: The Pile

Neuron 20 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1749952 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.7732. Min Act: -0.0000

Data Index: 224001 (The Pile)

Max Activating Token Index: 724

Text #2

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.7328. Min Act: -0.0000

Data Index: 984974 (The Pile)

Max Activating Token Index: 986

Text #3

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6275. Min Act: -0.0000

Data Index: 1751067 (The Pile)

Max Activating Token Index: 563

Text #4

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.7279. Min Act: -0.0000

Data Index: 928921 (The Pile)

Max Activating Token Index: 720

Text #5

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6121. Min Act: -0.0000

Data Index: 110503 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6495. Min Act: -0.0000

Data Index: 1122361 (The Pile)

Max Activating Token Index: 1001

Text #7

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6759. Min Act: -0.0000

Data Index: 375387 (The Pile)

Max Activating Token Index: 793

Text #8

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5992. Min Act: -0.0000

Data Index: 135042 (The Pile)

Max Activating Token Index: 130

Text #9

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1332718 (The Pile)

Max Activating Token Index: 98

Text #10

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1241479 (The Pile)

Max Activating Token Index: 148

Text #11

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1400274 (The Pile)

Max Activating Token Index: 186

Text #12

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1554344 (The Pile)

Max Activating Token Index: 377

Text #13

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5751. Min Act: -0.0000

Data Index: 723136 (The Pile)

Max Activating Token Index: 327

Text #14

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5545. Min Act: -0.0000

Data Index: 89565 (The Pile)

Max Activating Token Index: 948

Text #15

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5966. Min Act: -0.0000

Data Index: 1491502 (The Pile)

Max Activating Token Index: 787

Text #16

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5784. Min Act: -0.0000

Data Index: 857246 (The Pile)

Max Activating Token Index: 467

Text #17

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5921. Min Act: -0.0000

Data Index: 71080 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1446209 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 0.7946. Min Range: -0.7946

Max Act: 0.5251. Min Act: -0.0000

Data Index: 1624276 (The Pile)

Max Activating Token Index: 117