Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2761 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.4508. Min Act: -0.0000

Data Index: 615585 (The Pile)

Max Activating Token Index: 150

Text #1

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.4568. Min Act: -0.0000

Data Index: 1906468 (The Pile)

Max Activating Token Index: 383

Text #2

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.3099. Min Act: -0.0000

Data Index: 1488850 (The Pile)

Max Activating Token Index: 165

Text #3

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2362. Min Act: -0.0000

Data Index: 1625937 (The Pile)

Max Activating Token Index: 156

Text #4

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2896. Min Act: -0.0000

Data Index: 79575 (The Pile)

Max Activating Token Index: 176

Text #5

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2326. Min Act: -0.0000

Data Index: 729771 (The Pile)

Max Activating Token Index: 341

Text #6

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1925. Min Act: -0.0000

Data Index: 1503616 (The Pile)

Max Activating Token Index: 248

Text #7

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1628. Min Act: -0.0000

Data Index: 378379 (The Pile)

Max Activating Token Index: 182

Text #8

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1792. Min Act: -0.0000

Data Index: 1821158 (The Pile)

Max Activating Token Index: 68

Text #9

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1192. Min Act: -0.0000

Data Index: 10918 (The Pile)

Max Activating Token Index: 149

Text #10

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1010. Min Act: -0.0000

Data Index: 1495600 (The Pile)

Max Activating Token Index: 885

Text #11

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1110120 (The Pile)

Max Activating Token Index: 281

Text #12

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0865. Min Act: -0.0000

Data Index: 1551200 (The Pile)

Max Activating Token Index: 84

Text #13

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1184. Min Act: -0.0000

Data Index: 820233 (The Pile)

Max Activating Token Index: 106

Text #14

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0325. Min Act: -0.0000

Data Index: 1553665 (The Pile)

Max Activating Token Index: 668

Text #15

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.9929. Min Act: -0.0000

Data Index: 1858311 (The Pile)

Max Activating Token Index: 126

Text #16

Max Range: 1.4568. Min Range: -1.4568

Max Act: 0.9845. Min Act: -0.0000

Data Index: 642208 (The Pile)

Max Activating Token Index: 393

Text #17

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0124. Min Act: -0.0000

Data Index: 320121 (The Pile)

Max Activating Token Index: 687

Text #18

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0340. Min Act: -0.0000

Data Index: 878456 (The Pile)

Max Activating Token Index: 239

Text #19

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1693289 (The Pile)

Max Activating Token Index: 555