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

Dataset: The Pile

Neuron 1355 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: 1.3798. Min Range: -1.3798

Max Act: 1.3798. Min Act: -0.0000

Data Index: 655155 (The Pile)

Max Activating Token Index: 160

Text #1

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2513. Min Act: -0.0000

Data Index: 542032 (The Pile)

Max Activating Token Index: 800

Text #2

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.3354. Min Act: -0.0000

Data Index: 1563658 (The Pile)

Max Activating Token Index: 337

Text #3

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2152. Min Act: -0.0000

Data Index: 866269 (The Pile)

Max Activating Token Index: 204

Text #4

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1983. Min Act: -0.0000

Data Index: 82885 (The Pile)

Max Activating Token Index: 945

Text #5

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1032. Min Act: -0.0000

Data Index: 1259790 (The Pile)

Max Activating Token Index: 938

Text #6

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1614. Min Act: -0.0000

Data Index: 1495537 (The Pile)

Max Activating Token Index: 958

Text #7

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2311. Min Act: -0.0000

Data Index: 1565175 (The Pile)

Max Activating Token Index: 298

Text #8

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1326. Min Act: -0.0000

Data Index: 525774 (The Pile)

Max Activating Token Index: 480

Text #9

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1161. Min Act: -0.0000

Data Index: 1305947 (The Pile)

Max Activating Token Index: 839

Text #10

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1414. Min Act: -0.0000

Data Index: 95520 (The Pile)

Max Activating Token Index: 387

Text #11

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1329. Min Act: -0.0000

Data Index: 1649275 (The Pile)

Max Activating Token Index: 457

Text #12

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1201. Min Act: -0.0000

Data Index: 799727 (The Pile)

Max Activating Token Index: 390

Text #13

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1545. Min Act: -0.0000

Data Index: 1758885 (The Pile)

Max Activating Token Index: 784

Text #14

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1103. Min Act: -0.0000

Data Index: 1965760 (The Pile)

Max Activating Token Index: 432

Text #15

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0588. Min Act: -0.0000

Data Index: 469943 (The Pile)

Max Activating Token Index: 218

Text #16

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1321. Min Act: -0.0000

Data Index: 33327 (The Pile)

Max Activating Token Index: 353

Text #17

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0248. Min Act: -0.0000

Data Index: 1000622 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0873. Min Act: -0.0000

Data Index: 1076054 (The Pile)

Max Activating Token Index: 193

Text #19

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1845133 (The Pile)

Max Activating Token Index: 546