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

Dataset: The Pile

Neuron 4633 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: 1.3432. Min Range: -1.3432

Max Act: 1.3432. Min Act: -0.0000

Data Index: 597698 (The Pile)

Max Activating Token Index: 975

Text #1

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.1064. Min Act: -0.0000

Data Index: 978903 (The Pile)

Max Activating Token Index: 683

Text #2

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.1627. Min Act: -0.0000

Data Index: 944525 (The Pile)

Max Activating Token Index: 325

Text #3

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1361654 (The Pile)

Max Activating Token Index: 817

Text #4

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0672. Min Act: -0.0000

Data Index: 1056857 (The Pile)

Max Activating Token Index: 213

Text #5

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9685. Min Act: -0.0000

Data Index: 899837 (The Pile)

Max Activating Token Index: 177

Text #6

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9763. Min Act: -0.0000

Data Index: 1565916 (The Pile)

Max Activating Token Index: 466

Text #7

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0060. Min Act: -0.0000

Data Index: 1276877 (The Pile)

Max Activating Token Index: 258

Text #8

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0190. Min Act: -0.0000

Data Index: 1496016 (The Pile)

Max Activating Token Index: 791

Text #9

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1696960 (The Pile)

Max Activating Token Index: 416

Text #10

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0076. Min Act: -0.0000

Data Index: 1627089 (The Pile)

Max Activating Token Index: 72

Text #11

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9659. Min Act: -0.0000

Data Index: 1680986 (The Pile)

Max Activating Token Index: 834

Text #12

Max Range: 1.3432. Min Range: -1.3432

Max Act: 1.0435. Min Act: -0.0000

Data Index: 1111869 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9667. Min Act: -0.0000

Data Index: 766430 (The Pile)

Max Activating Token Index: 170

Text #14

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1100054 (The Pile)

Max Activating Token Index: 315

Text #15

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9536. Min Act: -0.0000

Data Index: 1971345 (The Pile)

Max Activating Token Index: 99

Text #16

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.9283. Min Act: -0.0000

Data Index: 773481 (The Pile)

Max Activating Token Index: 923

Text #17

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.8975. Min Act: -0.0000

Data Index: 864003 (The Pile)

Max Activating Token Index: 429

Text #18

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.8353. Min Act: -0.0000

Data Index: 941556 (The Pile)

Max Activating Token Index: 890

Text #19

Max Range: 1.3432. Min Range: -1.3432

Max Act: 0.8550. Min Act: -0.0000

Data Index: 1610311 (The Pile)

Max Activating Token Index: 94