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

Dataset: The Pile

Neuron 1773 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: 0.3995. Min Range: -0.3995

Max Act: 0.3824. Min Act: -0.0000

Data Index: 26915 (The Pile)

Max Activating Token Index: 278

Text #1

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3817. Min Act: -0.0000

Data Index: 698048 (The Pile)

Max Activating Token Index: 298

Text #2

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3952. Min Act: -0.0000

Data Index: 475346 (The Pile)

Max Activating Token Index: 813

Text #3

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3995. Min Act: -0.0000

Data Index: 1305574 (The Pile)

Max Activating Token Index: 800

Text #4

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3637. Min Act: -0.0000

Data Index: 121583 (The Pile)

Max Activating Token Index: 545

Text #5

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3642. Min Act: -0.0000

Data Index: 177921 (The Pile)

Max Activating Token Index: 690

Text #6

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3610. Min Act: -0.0000

Data Index: 48682 (The Pile)

Max Activating Token Index: 895

Text #7

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1500869 (The Pile)

Max Activating Token Index: 415

Text #8

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3272. Min Act: -0.0000

Data Index: 1089631 (The Pile)

Max Activating Token Index: 350

Text #9

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3213. Min Act: -0.0000

Data Index: 222892 (The Pile)

Max Activating Token Index: 784

Text #10

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1970430 (The Pile)

Max Activating Token Index: 754

Text #11

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.2979. Min Act: -0.0000

Data Index: 505750 (The Pile)

Max Activating Token Index: 869

Text #12

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3102. Min Act: -0.0000

Data Index: 1486354 (The Pile)

Max Activating Token Index: 440

Text #13

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1324450 (The Pile)

Max Activating Token Index: 236

Text #14

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3037. Min Act: -0.0000

Data Index: 1777979 (The Pile)

Max Activating Token Index: 34

Text #15

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1668245 (The Pile)

Max Activating Token Index: 806

Text #16

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.2860. Min Act: -0.0000

Data Index: 187423 (The Pile)

Max Activating Token Index: 803

Text #17

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1595876 (The Pile)

Max Activating Token Index: 959

Text #18

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1677729 (The Pile)

Max Activating Token Index: 1003

Text #19

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1388388 (The Pile)

Max Activating Token Index: 560