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

Dataset: The Pile

Neuron 4718 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.9906. Min Act: -0.0000

Data Index: 73290 (The Pile)

Max Activating Token Index: 711

Text #1

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1805223 (The Pile)

Max Activating Token Index: 105

Text #2

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.7202. Min Act: -0.0000

Data Index: 608707 (The Pile)

Max Activating Token Index: 69

Text #3

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1778304 (The Pile)

Max Activating Token Index: 911

Text #4

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.6684. Min Act: -0.0000

Data Index: 780379 (The Pile)

Max Activating Token Index: 133

Text #5

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.6711. Min Act: -0.0000

Data Index: 1948344 (The Pile)

Max Activating Token Index: 999

Text #6

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.6584. Min Act: -0.0000

Data Index: 909453 (The Pile)

Max Activating Token Index: 972

Text #7

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1295917 (The Pile)

Max Activating Token Index: 273

Text #8

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1631277 (The Pile)

Max Activating Token Index: 589

Text #9

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1686614 (The Pile)

Max Activating Token Index: 888

Text #10

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1096054 (The Pile)

Max Activating Token Index: 259

Text #11

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1095946 (The Pile)

Max Activating Token Index: 630

Text #12

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1156938 (The Pile)

Max Activating Token Index: 963

Text #13

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.5719. Min Act: -0.0000

Data Index: 185021 (The Pile)

Max Activating Token Index: 38

Text #14

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.5997. Min Act: -0.0000

Data Index: 708257 (The Pile)

Max Activating Token Index: 149

Text #15

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1587859 (The Pile)

Max Activating Token Index: 371

Text #16

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.5879. Min Act: -0.0000

Data Index: 323037 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1906048 (The Pile)

Max Activating Token Index: 932

Text #18

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1127827 (The Pile)

Max Activating Token Index: 264

Text #19

Max Range: 0.9906. Min Range: -0.9906

Max Act: 0.5991. Min Act: -0.0000

Data Index: 395237 (The Pile)

Max Activating Token Index: 756