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

Dataset: The Pile

Neuron 4970 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: 1.7567. Min Range: -1.7567

Max Act: 1.7567. Min Act: -0.0000

Data Index: 1391209 (The Pile)

Max Activating Token Index: 1005

Text #1

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.6987. Min Act: -0.0000

Data Index: 1094679 (The Pile)

Max Activating Token Index: 979

Text #2

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.5770. Min Act: -0.0000

Data Index: 283115 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.4162. Min Act: -0.0000

Data Index: 1660518 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.4181. Min Act: -0.0000

Data Index: 435248 (The Pile)

Max Activating Token Index: 282

Text #5

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.3756. Min Act: -0.0000

Data Index: 545848 (The Pile)

Max Activating Token Index: 339

Text #6

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.2881. Min Act: -0.0000

Data Index: 852926 (The Pile)

Max Activating Token Index: 878

Text #7

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.4091. Min Act: -0.0000

Data Index: 1356233 (The Pile)

Max Activating Token Index: 965

Text #8

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.2686. Min Act: -0.0000

Data Index: 1727774 (The Pile)

Max Activating Token Index: 37

Text #9

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.1742. Min Act: -0.0000

Data Index: 858637 (The Pile)

Max Activating Token Index: 798

Text #10

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.1753. Min Act: -0.0000

Data Index: 1921222 (The Pile)

Max Activating Token Index: 134

Text #11

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1132733 (The Pile)

Max Activating Token Index: 648

Text #12

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.0590. Min Act: -0.0000

Data Index: 1104217 (The Pile)

Max Activating Token Index: 782

Text #13

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.1626. Min Act: -0.0000

Data Index: 1608284 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.2057. Min Act: -0.0000

Data Index: 35052 (The Pile)

Max Activating Token Index: 270

Text #15

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.0408. Min Act: -0.0000

Data Index: 212955 (The Pile)

Max Activating Token Index: 647

Text #16

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.1250. Min Act: -0.0000

Data Index: 191904 (The Pile)

Max Activating Token Index: 482

Text #17

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.0523. Min Act: -0.0000

Data Index: 621881 (The Pile)

Max Activating Token Index: 451

Text #18

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.1049. Min Act: -0.0000

Data Index: 1093859 (The Pile)

Max Activating Token Index: 289

Text #19

Max Range: 1.7567. Min Range: -1.7567

Max Act: 1.0121. Min Act: -0.0000

Data Index: 795249 (The Pile)

Max Activating Token Index: 640