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

Dataset: The Pile

Neuron 2728 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: 1.3615. Min Range: -1.3615

Max Act: 1.3615. Min Act: -0.0000

Data Index: 1586401 (The Pile)

Max Activating Token Index: 788

Text #1

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.1877. Min Act: -0.0000

Data Index: 639711 (The Pile)

Max Activating Token Index: 889

Text #2

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.3288. Min Act: -0.0000

Data Index: 1031348 (The Pile)

Max Activating Token Index: 950

Text #3

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.2175. Min Act: -0.0000

Data Index: 193139 (The Pile)

Max Activating Token Index: 935

Text #4

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.0608. Min Act: -0.0000

Data Index: 1198515 (The Pile)

Max Activating Token Index: 1018

Text #5

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.2263. Min Act: -0.0000

Data Index: 139026 (The Pile)

Max Activating Token Index: 112

Text #6

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.1058. Min Act: -0.0000

Data Index: 1720311 (The Pile)

Max Activating Token Index: 468

Text #7

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.0321. Min Act: -0.0000

Data Index: 1686132 (The Pile)

Max Activating Token Index: 395

Text #8

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.0023. Min Act: 0.0000

Data Index: 1103287 (The Pile)

Max Activating Token Index: 494

Text #9

Max Range: 1.3615. Min Range: -1.3615

Max Act: 0.9542. Min Act: -0.0000

Data Index: 892600 (The Pile)

Max Activating Token Index: 232

Text #10

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.0241. Min Act: -0.0000

Data Index: 1391018 (The Pile)

Max Activating Token Index: 736

Text #11

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.0486. Min Act: -0.0000

Data Index: 979374 (The Pile)

Max Activating Token Index: 259

Text #12

Max Range: 1.3615. Min Range: -1.3615

Max Act: 0.7845. Min Act: -0.0000

Data Index: 265964 (The Pile)

Max Activating Token Index: 715

Text #13

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.2036. Min Act: -0.0000

Data Index: 1355327 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 1.3615. Min Range: -1.3615

Max Act: 0.9337. Min Act: -0.0000

Data Index: 1747147 (The Pile)

Max Activating Token Index: 901

Text #15

Max Range: 1.3615. Min Range: -1.3615

Max Act: 1.0093. Min Act: -0.0000

Data Index: 1333285 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 1.3615. Min Range: -1.3615

Max Act: 0.9609. Min Act: -0.0000

Data Index: 1636560 (The Pile)

Max Activating Token Index: 267

Text #17

Max Range: 1.3615. Min Range: -1.3615

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1103073 (The Pile)

Max Activating Token Index: 572

Text #18

Max Range: 1.3615. Min Range: -1.3615

Max Act: 0.8515. Min Act: -0.0000

Data Index: 204608 (The Pile)

Max Activating Token Index: 826

Text #19

Max Range: 1.3615. Min Range: -1.3615

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1651912 (The Pile)

Max Activating Token Index: 1017