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

Dataset: The Pile

Neuron 1138 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.4905. Min Act: -0.0000

Data Index: 90722 (The Pile)

Max Activating Token Index: 520

Text #1

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.4556. Min Act: -0.0000

Data Index: 466861 (The Pile)

Max Activating Token Index: 258

Text #2

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1156828 (The Pile)

Max Activating Token Index: 38

Text #3

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1407514 (The Pile)

Max Activating Token Index: 853

Text #4

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.4203. Min Act: -0.0000

Data Index: 1195528 (The Pile)

Max Activating Token Index: 568

Text #5

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1183367 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3625. Min Act: -0.0000

Data Index: 268328 (The Pile)

Max Activating Token Index: 905

Text #7

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1582341 (The Pile)

Max Activating Token Index: 32

Text #8

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3673. Min Act: -0.0000

Data Index: 78726 (The Pile)

Max Activating Token Index: 342

Text #9

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1388557 (The Pile)

Max Activating Token Index: 264

Text #10

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1160605 (The Pile)

Max Activating Token Index: 164

Text #11

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3325. Min Act: -0.0000

Data Index: 100884 (The Pile)

Max Activating Token Index: 250

Text #12

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3290. Min Act: -0.0000

Data Index: 917526 (The Pile)

Max Activating Token Index: 207

Text #13

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3319. Min Act: -0.0000

Data Index: 71129 (The Pile)

Max Activating Token Index: 565

Text #14

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3284. Min Act: -0.0000

Data Index: 272831 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3030. Min Act: -0.0000

Data Index: 11709 (The Pile)

Max Activating Token Index: 257

Text #16

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3324. Min Act: -0.0000

Data Index: 1321715 (The Pile)

Max Activating Token Index: 475

Text #17

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1380364 (The Pile)

Max Activating Token Index: 752

Text #18

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3166. Min Act: -0.0000

Data Index: 826191 (The Pile)

Max Activating Token Index: 110

Text #19

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3330. Min Act: -0.0000

Data Index: 559253 (The Pile)

Max Activating Token Index: 752