Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2235 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3619. Min Act: -0.0000

Data Index: 768308 (The Pile)

Max Activating Token Index: 452

Text #1

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2540. Min Act: -0.0000

Data Index: 306801 (The Pile)

Max Activating Token Index: 906

Text #2

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2532. Min Act: -0.0000

Data Index: 421649 (The Pile)

Max Activating Token Index: 485

Text #3

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2340. Min Act: -0.0000

Data Index: 756869 (The Pile)

Max Activating Token Index: 890

Text #4

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1037655 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1586969 (The Pile)

Max Activating Token Index: 951

Text #6

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2187. Min Act: -0.0000

Data Index: 1767425 (The Pile)

Max Activating Token Index: 809

Text #7

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1549714 (The Pile)

Max Activating Token Index: 726

Text #8

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2252. Min Act: -0.0000

Data Index: 32660 (The Pile)

Max Activating Token Index: 980

Text #9

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2164. Min Act: -0.0001

Data Index: 564379 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2238. Min Act: -0.0000

Data Index: 900178 (The Pile)

Max Activating Token Index: 528

Text #11

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2138. Min Act: -0.0000

Data Index: 238132 (The Pile)

Max Activating Token Index: 962

Text #12

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2191. Min Act: -0.0000

Data Index: 155995 (The Pile)

Max Activating Token Index: 740

Text #13

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2169. Min Act: -0.0000

Data Index: 671234 (The Pile)

Max Activating Token Index: 101

Text #14

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2174. Min Act: -0.0000

Data Index: 847218 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1486422 (The Pile)

Max Activating Token Index: 641

Text #16

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2072. Min Act: 0.0000

Data Index: 874646 (The Pile)

Max Activating Token Index: 988

Text #17

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1242853 (The Pile)

Max Activating Token Index: 888

Text #18

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.1998. Min Act: -0.0000

Data Index: 1117558 (The Pile)

Max Activating Token Index: 450

Text #19

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1855186 (The Pile)

Max Activating Token Index: 766