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

Dataset: The Pile

Neuron 3580 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.8732. Min Act: -0.0000

Data Index: 36534 (The Pile)

Max Activating Token Index: 979

Text #1

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.7602. Min Act: -0.0000

Data Index: 1657086 (The Pile)

Max Activating Token Index: 74

Text #2

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1834438 (The Pile)

Max Activating Token Index: 253

Text #3

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.7193. Min Act: -0.0000

Data Index: 676524 (The Pile)

Max Activating Token Index: 354

Text #4

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6859. Min Act: -0.0000

Data Index: 81884 (The Pile)

Max Activating Token Index: 894

Text #5

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1898826 (The Pile)

Max Activating Token Index: 286

Text #6

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1177452 (The Pile)

Max Activating Token Index: 329

Text #7

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6471. Min Act: -0.0000

Data Index: 1841474 (The Pile)

Max Activating Token Index: 38

Text #8

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.5758. Min Act: -0.0000

Data Index: 436105 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.7092. Min Act: -0.0000

Data Index: 523251 (The Pile)

Max Activating Token Index: 909

Text #10

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6363. Min Act: -0.0000

Data Index: 265217 (The Pile)

Max Activating Token Index: 686

Text #11

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6140. Min Act: -0.0000

Data Index: 829644 (The Pile)

Max Activating Token Index: 997

Text #12

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6126. Min Act: -0.0000

Data Index: 1179517 (The Pile)

Max Activating Token Index: 659

Text #13

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6116. Min Act: -0.0000

Data Index: 524136 (The Pile)

Max Activating Token Index: 453

Text #14

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6315. Min Act: -0.0000

Data Index: 662257 (The Pile)

Max Activating Token Index: 127

Text #15

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1731718 (The Pile)

Max Activating Token Index: 758

Text #16

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.5999. Min Act: -0.0000

Data Index: 211782 (The Pile)

Max Activating Token Index: 497

Text #17

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6169. Min Act: -0.0000

Data Index: 365409 (The Pile)

Max Activating Token Index: 324

Text #18

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1746030 (The Pile)

Max Activating Token Index: 825

Text #19

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1985974 (The Pile)

Max Activating Token Index: 978