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

Dataset: The Pile

Neuron 3159 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: 7.6310. Min Range: -7.6310

Max Act: 7.0509. Min Act: -0.0000

Data Index: 740384 (The Pile)

Max Activating Token Index: 882

Text #1

Max Range: 7.6310. Min Range: -7.6310

Max Act: 7.6310. Min Act: -0.0000

Data Index: 606525 (The Pile)

Max Activating Token Index: 536

Text #2

Max Range: 7.6310. Min Range: -7.6310

Max Act: 7.4416. Min Act: -0.0000

Data Index: 196348 (The Pile)

Max Activating Token Index: 726

Text #3

Max Range: 7.6310. Min Range: -7.6310

Max Act: 7.4167. Min Act: -0.0000

Data Index: 1425522 (The Pile)

Max Activating Token Index: 183

Text #4

Max Range: 7.6310. Min Range: -7.6310

Max Act: 6.0294. Min Act: -0.0000

Data Index: 497923 (The Pile)

Max Activating Token Index: 897

Text #5

Max Range: 7.6310. Min Range: -7.6310

Max Act: 6.0249. Min Act: -0.0000

Data Index: 1094733 (The Pile)

Max Activating Token Index: 895

Text #6

Max Range: 7.6310. Min Range: -7.6310

Max Act: 6.7572. Min Act: -0.0000

Data Index: 1313566 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 7.6310. Min Range: -7.6310

Max Act: 6.3099. Min Act: -0.0000

Data Index: 1685515 (The Pile)

Max Activating Token Index: 711

Text #8

Max Range: 7.6310. Min Range: -7.6310

Max Act: 6.4340. Min Act: -0.0000

Data Index: 1533132 (The Pile)

Max Activating Token Index: 212

Text #9

Max Range: 7.6310. Min Range: -7.6310

Max Act: 6.4165. Min Act: -0.0000

Data Index: 80549 (The Pile)

Max Activating Token Index: 273

Text #10

Max Range: 7.6310. Min Range: -7.6310

Max Act: 6.3932. Min Act: -0.0000

Data Index: 1296110 (The Pile)

Max Activating Token Index: 373

Text #11

Max Range: 7.6310. Min Range: -7.6310

Max Act: 5.4022. Min Act: -0.0000

Data Index: 1586449 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 7.6310. Min Range: -7.6310

Max Act: 6.8147. Min Act: -0.0000

Data Index: 991409 (The Pile)

Max Activating Token Index: 808

Text #13

Max Range: 7.6310. Min Range: -7.6310

Max Act: 6.4332. Min Act: -0.0000

Data Index: 884893 (The Pile)

Max Activating Token Index: 406

Text #14

Max Range: 7.6310. Min Range: -7.6310

Max Act: 5.9946. Min Act: -0.0000

Data Index: 1296375 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 7.6310. Min Range: -7.6310

Max Act: 6.1368. Min Act: -0.0000

Data Index: 1871091 (The Pile)

Max Activating Token Index: 301

Text #16

Max Range: 7.6310. Min Range: -7.6310

Max Act: 6.1956. Min Act: -0.0000

Data Index: 344811 (The Pile)

Max Activating Token Index: 279

Text #17

Max Range: 7.6310. Min Range: -7.6310

Max Act: 5.6331. Min Act: -0.0000

Data Index: 668421 (The Pile)

Max Activating Token Index: 206

Text #18

Max Range: 7.6310. Min Range: -7.6310

Max Act: 5.4647. Min Act: -0.0000

Data Index: 683077 (The Pile)

Max Activating Token Index: 868

Text #19

Max Range: 7.6310. Min Range: -7.6310

Max Act: 6.0563. Min Act: -0.0000

Data Index: 1577993 (The Pile)

Max Activating Token Index: 876