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

Dataset: The Pile

Neuron 1176 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.8026. Min Act: 0.0000

Data Index: 1928458 (The Pile)

Max Activating Token Index: 829

Text #1

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.8077. Min Act: -0.0000

Data Index: 336352 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.7576. Min Act: -0.0000

Data Index: 616640 (The Pile)

Max Activating Token Index: 104

Text #3

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1121675 (The Pile)

Max Activating Token Index: 86

Text #4

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6372. Min Act: -0.0000

Data Index: 771357 (The Pile)

Max Activating Token Index: 899

Text #5

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6868. Min Act: -0.0000

Data Index: 571867 (The Pile)

Max Activating Token Index: 947

Text #6

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6020. Min Act: -0.0000

Data Index: 507359 (The Pile)

Max Activating Token Index: 113

Text #7

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1586279 (The Pile)

Max Activating Token Index: 52

Text #8

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6655. Min Act: -0.0000

Data Index: 1006563 (The Pile)

Max Activating Token Index: 949

Text #9

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6193. Min Act: -0.0000

Data Index: 574088 (The Pile)

Max Activating Token Index: 847

Text #10

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1255978 (The Pile)

Max Activating Token Index: 871

Text #11

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1415605 (The Pile)

Max Activating Token Index: 1017

Text #12

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6236. Min Act: -0.0000

Data Index: 68748 (The Pile)

Max Activating Token Index: 471

Text #13

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1691772 (The Pile)

Max Activating Token Index: 459

Text #14

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1957113 (The Pile)

Max Activating Token Index: 480

Text #15

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1765495 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.6242. Min Act: -0.0000

Data Index: 1622380 (The Pile)

Max Activating Token Index: 130

Text #17

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1105260 (The Pile)

Max Activating Token Index: 985

Text #18

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1381142 (The Pile)

Max Activating Token Index: 480

Text #19

Max Range: 0.8077. Min Range: -0.8077

Max Act: 0.5804. Min Act: -0.0000

Data Index: 699832 (The Pile)

Max Activating Token Index: 720