Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2051 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1414. Min Range: -1.1414

Max Act: 1.1414. Min Act: -0.0000

Data Index: 879521 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 1.1414. Min Range: -1.1414

Max Act: 1.0550. Min Act: -0.0000

Data Index: 1909795 (The Pile)

Max Activating Token Index: 122

Text #2

Max Range: 1.1414. Min Range: -1.1414

Max Act: 1.0213. Min Act: -0.0000

Data Index: 1581882 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1693913 (The Pile)

Max Activating Token Index: 70

Text #4

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9880. Min Act: -0.0000

Data Index: 874519 (The Pile)

Max Activating Token Index: 339

Text #5

Max Range: 1.1414. Min Range: -1.1414

Max Act: 1.0331. Min Act: -0.0000

Data Index: 1603379 (The Pile)

Max Activating Token Index: 570

Text #6

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9470. Min Act: -0.0000

Data Index: 253017 (The Pile)

Max Activating Token Index: 729

Text #7

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9739. Min Act: -0.0000

Data Index: 1761024 (The Pile)

Max Activating Token Index: 222

Text #8

Max Range: 1.1414. Min Range: -1.1414

Max Act: 1.0098. Min Act: -0.0000

Data Index: 460408 (The Pile)

Max Activating Token Index: 699

Text #9

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9314. Min Act: -0.0000

Data Index: 1297061 (The Pile)

Max Activating Token Index: 129

Text #10

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9415. Min Act: -0.0000

Data Index: 807639 (The Pile)

Max Activating Token Index: 973

Text #11

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1993405 (The Pile)

Max Activating Token Index: 644

Text #12

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9089. Min Act: -0.0000

Data Index: 853128 (The Pile)

Max Activating Token Index: 27

Text #13

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9616. Min Act: -0.0000

Data Index: 1729313 (The Pile)

Max Activating Token Index: 17

Text #14

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9332. Min Act: -0.0000

Data Index: 1327596 (The Pile)

Max Activating Token Index: 182

Text #15

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8899. Min Act: -0.0000

Data Index: 1016398 (The Pile)

Max Activating Token Index: 35

Text #16

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9224. Min Act: -0.0000

Data Index: 1271855 (The Pile)

Max Activating Token Index: 324

Text #17

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9159. Min Act: -0.0000

Data Index: 1154023 (The Pile)

Max Activating Token Index: 616

Text #18

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.9145. Min Act: -0.0000

Data Index: 736519 (The Pile)

Max Activating Token Index: 667

Text #19

Max Range: 1.1414. Min Range: -1.1414

Max Act: 0.8850. Min Act: -0.0000

Data Index: 1766779 (The Pile)

Max Activating Token Index: 26