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

Dataset: The Pile

Neuron 3995 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 7.4962. Min Range: -7.4962

Max Act: 6.9951. Min Act: -0.0000

Data Index: 1708899 (The Pile)

Max Activating Token Index: 972

Text #1

Max Range: 7.4962. Min Range: -7.4962

Max Act: 7.4962. Min Act: -0.0000

Data Index: 710260 (The Pile)

Max Activating Token Index: 1012

Text #2

Max Range: 7.4962. Min Range: -7.4962

Max Act: 5.2704. Min Act: -0.0000

Data Index: 423216 (The Pile)

Max Activating Token Index: 912

Text #3

Max Range: 7.4962. Min Range: -7.4962

Max Act: 4.6483. Min Act: -0.0000

Data Index: 1926357 (The Pile)

Max Activating Token Index: 810

Text #4

Max Range: 7.4962. Min Range: -7.4962

Max Act: 3.8765. Min Act: -0.0000

Data Index: 107262 (The Pile)

Max Activating Token Index: 826

Text #5

Max Range: 7.4962. Min Range: -7.4962

Max Act: 3.4194. Min Act: -0.0000

Data Index: 157263 (The Pile)

Max Activating Token Index: 599

Text #6

Max Range: 7.4962. Min Range: -7.4962

Max Act: 3.8394. Min Act: -0.0000

Data Index: 250085 (The Pile)

Max Activating Token Index: 1013

Text #7

Max Range: 7.4962. Min Range: -7.4962

Max Act: 2.8998. Min Act: -0.0000

Data Index: 1274324 (The Pile)

Max Activating Token Index: 864

Text #8

Max Range: 7.4962. Min Range: -7.4962

Max Act: 3.6786. Min Act: -0.0000

Data Index: 534961 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 7.4962. Min Range: -7.4962

Max Act: 3.3008. Min Act: -0.0000

Data Index: 1788106 (The Pile)

Max Activating Token Index: 483

Text #10

Max Range: 7.4962. Min Range: -7.4962

Max Act: 2.2128. Min Act: -0.0000

Data Index: 619199 (The Pile)

Max Activating Token Index: 656

Text #11

Max Range: 7.4962. Min Range: -7.4962

Max Act: 2.6763. Min Act: -0.0000

Data Index: 8507 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 7.4962. Min Range: -7.4962

Max Act: 2.7275. Min Act: -0.0000

Data Index: 996099 (The Pile)

Max Activating Token Index: 926

Text #13

Max Range: 7.4962. Min Range: -7.4962

Max Act: 3.0228. Min Act: -0.0000

Data Index: 1352249 (The Pile)

Max Activating Token Index: 873

Text #14

Max Range: 7.4962. Min Range: -7.4962

Max Act: 2.8592. Min Act: -0.0000

Data Index: 203318 (The Pile)

Max Activating Token Index: 917

Text #15

Max Range: 7.4962. Min Range: -7.4962

Max Act: 2.8903. Min Act: -0.0000

Data Index: 1910963 (The Pile)

Max Activating Token Index: 791

Text #16

Max Range: 7.4962. Min Range: -7.4962

Max Act: 2.6309. Min Act: -0.0000

Data Index: 1105260 (The Pile)

Max Activating Token Index: 374

Text #17

Max Range: 7.4962. Min Range: -7.4962

Max Act: 3.1898. Min Act: -0.0000

Data Index: 517702 (The Pile)

Max Activating Token Index: 818

Text #18

Max Range: 7.4962. Min Range: -7.4962

Max Act: 2.8867. Min Act: -0.0000

Data Index: 179395 (The Pile)

Max Activating Token Index: 719

Text #19

Max Range: 7.4962. Min Range: -7.4962

Max Act: 2.7800. Min Act: -0.0000

Data Index: 1974251 (The Pile)

Max Activating Token Index: 795