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

Dataset: The Pile

Neuron 3888 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9021. Min Act: -0.0000

Data Index: 296880 (The Pile)

Max Activating Token Index: 158

Text #1

Max Range: 1.0779. Min Range: -1.0779

Max Act: 1.0001. Min Act: -0.0000

Data Index: 123370 (The Pile)

Max Activating Token Index: 438

Text #2

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9981. Min Act: -0.0000

Data Index: 868923 (The Pile)

Max Activating Token Index: 103

Text #3

Max Range: 1.0779. Min Range: -1.0779

Max Act: 1.0779. Min Act: -0.0000

Data Index: 604703 (The Pile)

Max Activating Token Index: 401

Text #4

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8986. Min Act: -0.0000

Data Index: 254333 (The Pile)

Max Activating Token Index: 685

Text #5

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8246. Min Act: -0.0000

Data Index: 269270 (The Pile)

Max Activating Token Index: 712

Text #6

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8567. Min Act: -0.0000

Data Index: 1337395 (The Pile)

Max Activating Token Index: 130

Text #7

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9224. Min Act: -0.0000

Data Index: 875200 (The Pile)

Max Activating Token Index: 109

Text #8

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8189. Min Act: -0.0000

Data Index: 14562 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8380. Min Act: -0.0000

Data Index: 1156132 (The Pile)

Max Activating Token Index: 390

Text #10

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1767966 (The Pile)

Max Activating Token Index: 500

Text #11

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9382. Min Act: -0.0000

Data Index: 1161194 (The Pile)

Max Activating Token Index: 222

Text #12

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9580. Min Act: -0.0000

Data Index: 1864736 (The Pile)

Max Activating Token Index: 361

Text #13

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.7346. Min Act: -0.0000

Data Index: 1147824 (The Pile)

Max Activating Token Index: 38

Text #14

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8386. Min Act: -0.0000

Data Index: 1698310 (The Pile)

Max Activating Token Index: 571

Text #15

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.9753. Min Act: -0.0000

Data Index: 950732 (The Pile)

Max Activating Token Index: 441

Text #16

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1021580 (The Pile)

Max Activating Token Index: 528

Text #17

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.7457. Min Act: -0.0000

Data Index: 836480 (The Pile)

Max Activating Token Index: 62

Text #18

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8342. Min Act: -0.0000

Data Index: 1551621 (The Pile)

Max Activating Token Index: 200

Text #19

Max Range: 1.0779. Min Range: -1.0779

Max Act: 0.8159. Min Act: -0.0000

Data Index: 1655883 (The Pile)

Max Activating Token Index: 194