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

Dataset: The Pile

Neuron 3873 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: 0.2441. Min Range: -0.2441

Max Act: 0.2441. Min Act: -0.0000

Data Index: 1264812 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2340. Min Act: -0.0000

Data Index: 1523106 (The Pile)

Max Activating Token Index: 264

Text #2

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1813006 (The Pile)

Max Activating Token Index: 170

Text #3

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1137555 (The Pile)

Max Activating Token Index: 91

Text #4

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2163. Min Act: -0.0000

Data Index: 209714 (The Pile)

Max Activating Token Index: 622

Text #5

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1337026 (The Pile)

Max Activating Token Index: 923

Text #6

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2110. Min Act: -0.0000

Data Index: 318340 (The Pile)

Max Activating Token Index: 940

Text #7

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2012. Min Act: -0.0000

Data Index: 196376 (The Pile)

Max Activating Token Index: 705

Text #8

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1557126 (The Pile)

Max Activating Token Index: 736

Text #9

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1970. Min Act: -0.0000

Data Index: 231872 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2015. Min Act: -0.0000

Data Index: 555001 (The Pile)

Max Activating Token Index: 289

Text #11

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1986. Min Act: -0.0000

Data Index: 159971 (The Pile)

Max Activating Token Index: 271

Text #12

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1482252 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1919. Min Act: -0.0000

Data Index: 97641 (The Pile)

Max Activating Token Index: 244

Text #14

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1971. Min Act: -0.0000

Data Index: 41668 (The Pile)

Max Activating Token Index: 132

Text #15

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2042. Min Act: -0.0000

Data Index: 903391 (The Pile)

Max Activating Token Index: 803

Text #16

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1878. Min Act: -0.0000

Data Index: 284667 (The Pile)

Max Activating Token Index: 108

Text #17

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2067. Min Act: -0.0000

Data Index: 1401249 (The Pile)

Max Activating Token Index: 918

Text #18

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1922. Min Act: -0.0000

Data Index: 424616 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1929. Min Act: 0.0000

Data Index: 857417 (The Pile)

Max Activating Token Index: 98