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

Dataset: The Pile

Neuron 4548 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5307. Min Range: -1.5307

Max Act: 1.5307. Min Act: -0.0000

Data Index: 757955 (The Pile)

Max Activating Token Index: 182

Text #1

Max Range: 1.5307. Min Range: -1.5307

Max Act: 1.2428. Min Act: -0.0000

Data Index: 1162406 (The Pile)

Max Activating Token Index: 793

Text #2

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.9224. Min Act: -0.0000

Data Index: 1432928 (The Pile)

Max Activating Token Index: 90

Text #3

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.7070. Min Act: -0.0000

Data Index: 555293 (The Pile)

Max Activating Token Index: 982

Text #4

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.8752. Min Act: -0.0000

Data Index: 777835 (The Pile)

Max Activating Token Index: 724

Text #5

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1940491 (The Pile)

Max Activating Token Index: 675

Text #6

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.6245. Min Act: -0.0000

Data Index: 107900 (The Pile)

Max Activating Token Index: 877

Text #7

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.6593. Min Act: -0.0000

Data Index: 180868 (The Pile)

Max Activating Token Index: 421

Text #8

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.6629. Min Act: -0.0000

Data Index: 951208 (The Pile)

Max Activating Token Index: 163

Text #9

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1775194 (The Pile)

Max Activating Token Index: 743

Text #10

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.6202. Min Act: -0.0000

Data Index: 960003 (The Pile)

Max Activating Token Index: 689

Text #11

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.6229. Min Act: -0.0000

Data Index: 843132 (The Pile)

Max Activating Token Index: 945

Text #12

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.6318. Min Act: -0.0000

Data Index: 279971 (The Pile)

Max Activating Token Index: 942

Text #13

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.6057. Min Act: -0.0000

Data Index: 207365 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.5610. Min Act: -0.0000

Data Index: 432394 (The Pile)

Max Activating Token Index: 279

Text #15

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.5779. Min Act: -0.0000

Data Index: 230079 (The Pile)

Max Activating Token Index: 784

Text #16

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.5969. Min Act: -0.0000

Data Index: 755246 (The Pile)

Max Activating Token Index: 170

Text #17

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.5922. Min Act: -0.0000

Data Index: 844941 (The Pile)

Max Activating Token Index: 237

Text #18

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.6511. Min Act: -0.0000

Data Index: 361629 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 1.5307. Min Range: -1.5307

Max Act: 0.5796. Min Act: -0.0000

Data Index: 1802331 (The Pile)

Max Activating Token Index: 614