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

Dataset: The Pile

Neuron 718 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: 0.5894. Min Range: -0.5894

Max Act: 0.5894. Min Act: -0.0000

Data Index: 511523 (The Pile)

Max Activating Token Index: 668

Text #1

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1607945 (The Pile)

Max Activating Token Index: 553

Text #2

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.5228. Min Act: -0.0000

Data Index: 371972 (The Pile)

Max Activating Token Index: 918

Text #3

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.5204. Min Act: -0.0000

Data Index: 620005 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.5194. Min Act: -0.0000

Data Index: 737550 (The Pile)

Max Activating Token Index: 864

Text #5

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1535457 (The Pile)

Max Activating Token Index: 64

Text #6

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.5211. Min Act: -0.0000

Data Index: 585470 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1530773 (The Pile)

Max Activating Token Index: 824

Text #8

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4986. Min Act: 0.0000

Data Index: 1474399 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.5147. Min Act: -0.0000

Data Index: 88082 (The Pile)

Max Activating Token Index: 208

Text #10

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4725. Min Act: -0.0000

Data Index: 941044 (The Pile)

Max Activating Token Index: 890

Text #11

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4896. Min Act: -0.0000

Data Index: 96398 (The Pile)

Max Activating Token Index: 862

Text #12

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1921086 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1926183 (The Pile)

Max Activating Token Index: 57

Text #14

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4846. Min Act: -0.0000

Data Index: 1161778 (The Pile)

Max Activating Token Index: 476

Text #15

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1033912 (The Pile)

Max Activating Token Index: 592

Text #16

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1805155 (The Pile)

Max Activating Token Index: 239

Text #17

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1430872 (The Pile)

Max Activating Token Index: 284

Text #18

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4684. Min Act: -0.0000

Data Index: 438434 (The Pile)

Max Activating Token Index: 638

Text #19

Max Range: 0.5894. Min Range: -0.5894

Max Act: 0.4968. Min Act: -0.0000

Data Index: 205465 (The Pile)

Max Activating Token Index: 480