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

Dataset: The Pile

Neuron 3316 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: 0.9966. Min Range: -0.9966

Max Act: 0.9966. Min Act: -0.0000

Data Index: 882103 (The Pile)

Max Activating Token Index: 113

Text #1

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.8424. Min Act: -0.0000

Data Index: 1625832 (The Pile)

Max Activating Token Index: 494

Text #2

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7541. Min Act: -0.0000

Data Index: 1579983 (The Pile)

Max Activating Token Index: 445

Text #3

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7732. Min Act: -0.0000

Data Index: 1581974 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6661. Min Act: -0.0000

Data Index: 72864 (The Pile)

Max Activating Token Index: 597

Text #5

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7172. Min Act: -0.0000

Data Index: 486705 (The Pile)

Max Activating Token Index: 97

Text #6

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7178. Min Act: -0.0000

Data Index: 703251 (The Pile)

Max Activating Token Index: 888

Text #7

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1784594 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1380438 (The Pile)

Max Activating Token Index: 76

Text #9

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7064. Min Act: -0.0000

Data Index: 1793212 (The Pile)

Max Activating Token Index: 55

Text #10

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1208447 (The Pile)

Max Activating Token Index: 942

Text #11

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1367073 (The Pile)

Max Activating Token Index: 440

Text #12

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.5538. Min Act: -0.0000

Data Index: 410587 (The Pile)

Max Activating Token Index: 415

Text #13

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1166288 (The Pile)

Max Activating Token Index: 580

Text #14

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.5743. Min Act: -0.0000

Data Index: 712666 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6069. Min Act: -0.0000

Data Index: 1885701 (The Pile)

Max Activating Token Index: 866

Text #16

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.5579. Min Act: -0.0000

Data Index: 592837 (The Pile)

Max Activating Token Index: 802

Text #17

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6000. Min Act: -0.0000

Data Index: 299169 (The Pile)

Max Activating Token Index: 360

Text #18

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.5596. Min Act: -0.0000

Data Index: 767270 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1456922 (The Pile)

Max Activating Token Index: 388