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

Dataset: The Pile

Neuron 475 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.4036. Min Act: -0.0000

Data Index: 292570 (The Pile)

Max Activating Token Index: 465

Text #1

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1932554 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3513. Min Act: -0.0000

Data Index: 959491 (The Pile)

Max Activating Token Index: 215

Text #3

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3126. Min Act: -0.0000

Data Index: 1750956 (The Pile)

Max Activating Token Index: 447

Text #4

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3211. Min Act: -0.0000

Data Index: 438565 (The Pile)

Max Activating Token Index: 548

Text #5

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3113. Min Act: -0.0000

Data Index: 1209953 (The Pile)

Max Activating Token Index: 434

Text #6

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1530761 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1415605 (The Pile)

Max Activating Token Index: 895

Text #8

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2908. Min Act: -0.0000

Data Index: 1300097 (The Pile)

Max Activating Token Index: 988

Text #9

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1785459 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1882444 (The Pile)

Max Activating Token Index: 552

Text #11

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3247. Min Act: -0.0000

Data Index: 290741 (The Pile)

Max Activating Token Index: 568

Text #12

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1687629 (The Pile)

Max Activating Token Index: 577

Text #13

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1374837 (The Pile)

Max Activating Token Index: 354

Text #14

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2834. Min Act: 0.0000

Data Index: 1004043 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3021. Min Act: -0.0000

Data Index: 326894 (The Pile)

Max Activating Token Index: 57

Text #16

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2970. Min Act: -0.0000

Data Index: 1249070 (The Pile)

Max Activating Token Index: 1005

Text #17

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2799. Min Act: -0.0000

Data Index: 967205 (The Pile)

Max Activating Token Index: 145

Text #18

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1245762 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2851. Min Act: 0.0000

Data Index: 1757179 (The Pile)

Max Activating Token Index: 138