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

Dataset: The Pile

Neuron 3576 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1788030 (The Pile)

Max Activating Token Index: 673

Text #1

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2506. Min Act: -0.0000

Data Index: 32947 (The Pile)

Max Activating Token Index: 899

Text #2

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2808. Min Act: -0.0000

Data Index: 1848223 (The Pile)

Max Activating Token Index: 25

Text #3

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2585. Min Act: -0.0000

Data Index: 809376 (The Pile)

Max Activating Token Index: 141

Text #4

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2654. Min Act: -0.0000

Data Index: 326913 (The Pile)

Max Activating Token Index: 434

Text #5

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2405. Min Act: -0.0000

Data Index: 130234 (The Pile)

Max Activating Token Index: 860

Text #6

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2264. Min Act: -0.0000

Data Index: 1997964 (The Pile)

Max Activating Token Index: 885

Text #7

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1108213 (The Pile)

Max Activating Token Index: 999

Text #8

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2163. Min Act: -0.0000

Data Index: 393316 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1363936 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2284. Min Act: -0.0000

Data Index: 323991 (The Pile)

Max Activating Token Index: 365

Text #11

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1971830 (The Pile)

Max Activating Token Index: 543

Text #12

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2038. Min Act: -0.0000

Data Index: 962265 (The Pile)

Max Activating Token Index: 721

Text #13

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1766937 (The Pile)

Max Activating Token Index: 982

Text #14

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2045. Min Act: -0.0000

Data Index: 393459 (The Pile)

Max Activating Token Index: 30

Text #15

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1768915 (The Pile)

Max Activating Token Index: 295

Text #16

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1680245 (The Pile)

Max Activating Token Index: 86

Text #17

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1412503 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.2088. Min Act: -0.0000

Data Index: 735420 (The Pile)

Max Activating Token Index: 100

Text #19

Max Range: 0.3096. Min Range: -0.3096

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1651846 (The Pile)

Max Activating Token Index: 945