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

Dataset: The Pile

Neuron 4602 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.3978. Min Act: -0.0000

Data Index: 235871 (The Pile)

Max Activating Token Index: 862

Text #1

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.2954. Min Act: -0.0000

Data Index: 827928 (The Pile)

Max Activating Token Index: 733

Text #2

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.2849. Min Act: -0.0000

Data Index: 1940754 (The Pile)

Max Activating Token Index: 309

Text #3

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.1538. Min Act: 0.0000

Data Index: 1827396 (The Pile)

Max Activating Token Index: 128

Text #4

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.1575. Min Act: -0.0000

Data Index: 1714695 (The Pile)

Max Activating Token Index: 571

Text #5

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0933. Min Act: -0.0000

Data Index: 253191 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.1507. Min Act: -0.0000

Data Index: 1482229 (The Pile)

Max Activating Token Index: 313

Text #7

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.2585. Min Act: 0.0000

Data Index: 956614 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.8726. Min Act: -0.0000

Data Index: 918225 (The Pile)

Max Activating Token Index: 877

Text #9

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.2208. Min Act: -0.0000

Data Index: 124024 (The Pile)

Max Activating Token Index: 248

Text #10

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.2179. Min Act: -0.0000

Data Index: 1236472 (The Pile)

Max Activating Token Index: 215

Text #11

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.2179. Min Act: -0.0000

Data Index: 578373 (The Pile)

Max Activating Token Index: 215

Text #12

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.1214. Min Act: -0.0000

Data Index: 707710 (The Pile)

Max Activating Token Index: 451

Text #13

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1670881 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.3357. Min Act: -0.0000

Data Index: 529321 (The Pile)

Max Activating Token Index: 578

Text #15

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0938. Min Act: -0.0000

Data Index: 584565 (The Pile)

Max Activating Token Index: 179

Text #16

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0906. Min Act: -0.0000

Data Index: 1632825 (The Pile)

Max Activating Token Index: 656

Text #17

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0779. Min Act: 0.0000

Data Index: 234468 (The Pile)

Max Activating Token Index: 705

Text #18

Max Range: 1.3978. Min Range: -1.3978

Max Act: 1.0019. Min Act: 0.0001

Data Index: 1632076 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 1.3978. Min Range: -1.3978

Max Act: 0.8538. Min Act: -0.0000

Data Index: 223545 (The Pile)

Max Activating Token Index: 782