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

Dataset: The Pile

Neuron 1705 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: 1.6874. Min Range: -1.6874

Max Act: 1.6874. Min Act: -0.0000

Data Index: 315822 (The Pile)

Max Activating Token Index: 228

Text #1

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.4667. Min Act: -0.0000

Data Index: 149520 (The Pile)

Max Activating Token Index: 852

Text #2

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.4395. Min Act: -0.0000

Data Index: 1079898 (The Pile)

Max Activating Token Index: 814

Text #3

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.5000. Min Act: -0.0000

Data Index: 585110 (The Pile)

Max Activating Token Index: 371

Text #4

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.3316. Min Act: -0.0000

Data Index: 1232608 (The Pile)

Max Activating Token Index: 408

Text #5

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.4895. Min Act: -0.0000

Data Index: 1693189 (The Pile)

Max Activating Token Index: 845

Text #6

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.3400. Min Act: -0.0000

Data Index: 908260 (The Pile)

Max Activating Token Index: 340

Text #7

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.4171. Min Act: -0.0000

Data Index: 920882 (The Pile)

Max Activating Token Index: 413

Text #8

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.2573. Min Act: -0.0000

Data Index: 749034 (The Pile)

Max Activating Token Index: 196

Text #9

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.4380. Min Act: -0.0000

Data Index: 975297 (The Pile)

Max Activating Token Index: 853

Text #10

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.3122. Min Act: -0.0000

Data Index: 1896888 (The Pile)

Max Activating Token Index: 896

Text #11

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.2213. Min Act: -0.0000

Data Index: 197871 (The Pile)

Max Activating Token Index: 206

Text #12

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.2842. Min Act: -0.0000

Data Index: 948803 (The Pile)

Max Activating Token Index: 1002

Text #13

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.2022. Min Act: -0.0000

Data Index: 418950 (The Pile)

Max Activating Token Index: 805

Text #14

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.4520. Min Act: -0.0000

Data Index: 1520040 (The Pile)

Max Activating Token Index: 926

Text #15

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.3549. Min Act: -0.0000

Data Index: 1058493 (The Pile)

Max Activating Token Index: 889

Text #16

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.0709. Min Act: -0.0000

Data Index: 1680489 (The Pile)

Max Activating Token Index: 360

Text #17

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.2021. Min Act: -0.0000

Data Index: 1814742 (The Pile)

Max Activating Token Index: 989

Text #18

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.1651. Min Act: -0.0000

Data Index: 276899 (The Pile)

Max Activating Token Index: 352

Text #19

Max Range: 1.6874. Min Range: -1.6874

Max Act: 1.1687. Min Act: -0.0000

Data Index: 1943207 (The Pile)

Max Activating Token Index: 507