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

Dataset: The Pile

Neuron 1999 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3119. Min Act: -0.0000

Data Index: 1228489 (The Pile)

Max Activating Token Index: 586

Text #1

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3262. Min Act: -0.0000

Data Index: 553974 (The Pile)

Max Activating Token Index: 847

Text #2

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3329. Min Act: -0.0000

Data Index: 214250 (The Pile)

Max Activating Token Index: 345

Text #3

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1966361 (The Pile)

Max Activating Token Index: 57

Text #4

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3085. Min Act: -0.0000

Data Index: 364644 (The Pile)

Max Activating Token Index: 272

Text #5

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1844202 (The Pile)

Max Activating Token Index: 140

Text #6

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3250. Min Act: -0.0000

Data Index: 1988850 (The Pile)

Max Activating Token Index: 101

Text #7

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3059. Min Act: -0.0000

Data Index: 1360032 (The Pile)

Max Activating Token Index: 615

Text #8

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3102. Min Act: -0.0000

Data Index: 96058 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2984. Min Act: -0.0000

Data Index: 265123 (The Pile)

Max Activating Token Index: 112

Text #10

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2914. Min Act: -0.0000

Data Index: 306994 (The Pile)

Max Activating Token Index: 575

Text #11

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1230222 (The Pile)

Max Activating Token Index: 497

Text #12

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1711807 (The Pile)

Max Activating Token Index: 370

Text #13

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3090. Min Act: -0.0000

Data Index: 1332049 (The Pile)

Max Activating Token Index: 932

Text #14

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2887. Min Act: -0.0000

Data Index: 303630 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2745. Min Act: -0.0000

Data Index: 1542375 (The Pile)

Max Activating Token Index: 312

Text #16

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1710416 (The Pile)

Max Activating Token Index: 826

Text #17

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2827. Min Act: -0.0000

Data Index: 309429 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2814. Min Act: -0.0000

Data Index: 150538 (The Pile)

Max Activating Token Index: 1016

Text #19

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2870. Min Act: -0.0000

Data Index: 667073 (The Pile)

Max Activating Token Index: 471