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

Dataset: The Pile

Neuron 2435 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.3134. Min Act: -0.0000

Data Index: 503076 (The Pile)

Max Activating Token Index: 725

Text #1

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2703. Min Act: -0.0000

Data Index: 992263 (The Pile)

Max Activating Token Index: 940

Text #2

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2318. Min Act: -0.0000

Data Index: 564218 (The Pile)

Max Activating Token Index: 792

Text #3

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1553311 (The Pile)

Max Activating Token Index: 502

Text #4

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.2036. Min Act: -0.0000

Data Index: 1936106 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1992203 (The Pile)

Max Activating Token Index: 246

Text #6

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1802. Min Act: -0.0000

Data Index: 193444 (The Pile)

Max Activating Token Index: 853

Text #7

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1216503 (The Pile)

Max Activating Token Index: 502

Text #8

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1975. Min Act: -0.0000

Data Index: 1647896 (The Pile)

Max Activating Token Index: 546

Text #9

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1989. Min Act: -0.0000

Data Index: 795793 (The Pile)

Max Activating Token Index: 947

Text #10

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1982. Min Act: -0.0000

Data Index: 210434 (The Pile)

Max Activating Token Index: 955

Text #11

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1983. Min Act: -0.0000

Data Index: 120125 (The Pile)

Max Activating Token Index: 710

Text #12

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1390996 (The Pile)

Max Activating Token Index: 536

Text #13

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1705. Min Act: -0.0000

Data Index: 1988947 (The Pile)

Max Activating Token Index: 212

Text #14

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1737. Min Act: -0.0000

Data Index: 192831 (The Pile)

Max Activating Token Index: 192

Text #15

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1612. Min Act: -0.0000

Data Index: 1275500 (The Pile)

Max Activating Token Index: 1013

Text #16

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1528906 (The Pile)

Max Activating Token Index: 995

Text #17

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1708. Min Act: -0.0000

Data Index: 896703 (The Pile)

Max Activating Token Index: 780

Text #18

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1646. Min Act: -0.0000

Data Index: 74674 (The Pile)

Max Activating Token Index: 716

Text #19

Max Range: 0.3134. Min Range: -0.3134

Max Act: 0.1718. Min Act: -0.0000

Data Index: 793987 (The Pile)

Max Activating Token Index: 814