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

Dataset: The Pile

Neuron 4290 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: 1.7108. Min Range: -1.7108

Max Act: 1.5957. Min Act: -0.0000

Data Index: 889788 (The Pile)

Max Activating Token Index: 180

Text #1

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.4925. Min Act: -0.0000

Data Index: 1684365 (The Pile)

Max Activating Token Index: 43

Text #2

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.1363. Min Act: -0.0000

Data Index: 1849337 (The Pile)

Max Activating Token Index: 814

Text #3

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.2267. Min Act: -0.0000

Data Index: 537514 (The Pile)

Max Activating Token Index: 131

Text #4

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.3623. Min Act: -0.0000

Data Index: 1395461 (The Pile)

Max Activating Token Index: 594

Text #5

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.7108. Min Act: -0.0000

Data Index: 242807 (The Pile)

Max Activating Token Index: 170

Text #6

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.0799. Min Act: -0.0000

Data Index: 1705770 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.2055. Min Act: -0.0000

Data Index: 1612242 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.2255. Min Act: -0.0000

Data Index: 1382995 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.1478. Min Act: -0.0000

Data Index: 1369917 (The Pile)

Max Activating Token Index: 215

Text #10

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.2088. Min Act: -0.0000

Data Index: 461337 (The Pile)

Max Activating Token Index: 701

Text #11

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.1226. Min Act: -0.0000

Data Index: 1647607 (The Pile)

Max Activating Token Index: 102

Text #12

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1780817 (The Pile)

Max Activating Token Index: 515

Text #13

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.0929. Min Act: -0.0000

Data Index: 921432 (The Pile)

Max Activating Token Index: 93

Text #14

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.0873. Min Act: -0.0000

Data Index: 896572 (The Pile)

Max Activating Token Index: 552

Text #15

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.1004. Min Act: -0.0000

Data Index: 1762783 (The Pile)

Max Activating Token Index: 677

Text #16

Max Range: 1.7108. Min Range: -1.7108

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1626915 (The Pile)

Max Activating Token Index: 364

Text #17

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.0510. Min Act: -0.0000

Data Index: 1913239 (The Pile)

Max Activating Token Index: 728

Text #18

Max Range: 1.7108. Min Range: -1.7108

Max Act: 0.9777. Min Act: -0.0000

Data Index: 520301 (The Pile)

Max Activating Token Index: 486

Text #19

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.1267. Min Act: -0.0000

Data Index: 1578999 (The Pile)

Max Activating Token Index: 909