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

Dataset: The Pile

Neuron 2651 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1293923 (The Pile)

Max Activating Token Index: 661

Text #1

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3578. Min Act: -0.0000

Data Index: 992198 (The Pile)

Max Activating Token Index: 955

Text #2

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1746627 (The Pile)

Max Activating Token Index: 847

Text #3

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3327. Min Act: -0.0000

Data Index: 1135446 (The Pile)

Max Activating Token Index: 156

Text #4

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3359. Min Act: -0.0000

Data Index: 853298 (The Pile)

Max Activating Token Index: 215

Text #5

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3192. Min Act: -0.0000

Data Index: 1640530 (The Pile)

Max Activating Token Index: 168

Text #6

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3198. Min Act: -0.0000

Data Index: 376350 (The Pile)

Max Activating Token Index: 55

Text #7

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1468652 (The Pile)

Max Activating Token Index: 427

Text #8

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3094. Min Act: -0.0000

Data Index: 1131836 (The Pile)

Max Activating Token Index: 771

Text #9

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3485. Min Act: -0.0000

Data Index: 133869 (The Pile)

Max Activating Token Index: 981

Text #10

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2699. Min Act: -0.0000

Data Index: 496205 (The Pile)

Max Activating Token Index: 929

Text #11

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1563891 (The Pile)

Max Activating Token Index: 539

Text #12

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1687265 (The Pile)

Max Activating Token Index: 258

Text #13

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2965. Min Act: -0.0000

Data Index: 1674167 (The Pile)

Max Activating Token Index: 697

Text #14

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2977. Min Act: -0.0000

Data Index: 353060 (The Pile)

Max Activating Token Index: 462

Text #15

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2957. Min Act: -0.0000

Data Index: 1219098 (The Pile)

Max Activating Token Index: 360

Text #16

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2837. Min Act: -0.0000

Data Index: 522780 (The Pile)

Max Activating Token Index: 960

Text #17

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3027. Min Act: -0.0000

Data Index: 1523 (The Pile)

Max Activating Token Index: 494

Text #18

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1853288 (The Pile)

Max Activating Token Index: 34

Text #19

Max Range: 0.3621. Min Range: -0.3621

Max Act: 0.2947. Min Act: -0.0000

Data Index: 422689 (The Pile)

Max Activating Token Index: 949