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

Dataset: The Pile

Neuron 1745 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: 0.8424. Min Range: -0.8424

Max Act: 0.8424. Min Act: -0.0000

Data Index: 147489 (The Pile)

Max Activating Token Index: 80

Text #1

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.7761. Min Act: -0.0000

Data Index: 106261 (The Pile)

Max Activating Token Index: 43

Text #2

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6979. Min Act: -0.0000

Data Index: 230102 (The Pile)

Max Activating Token Index: 659

Text #3

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.7001. Min Act: -0.0000

Data Index: 459573 (The Pile)

Max Activating Token Index: 193

Text #4

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1508696 (The Pile)

Max Activating Token Index: 103

Text #5

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6619. Min Act: -0.0000

Data Index: 659786 (The Pile)

Max Activating Token Index: 371

Text #6

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6974. Min Act: -0.0000

Data Index: 1697966 (The Pile)

Max Activating Token Index: 78

Text #7

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1864594 (The Pile)

Max Activating Token Index: 769

Text #8

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6686. Min Act: -0.0000

Data Index: 280642 (The Pile)

Max Activating Token Index: 329

Text #9

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1106954 (The Pile)

Max Activating Token Index: 186

Text #10

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1996948 (The Pile)

Max Activating Token Index: 21

Text #11

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1591135 (The Pile)

Max Activating Token Index: 26

Text #12

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1040470 (The Pile)

Max Activating Token Index: 21

Text #13

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1946596 (The Pile)

Max Activating Token Index: 60

Text #14

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1269048 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.6220. Min Act: -0.0000

Data Index: 608792 (The Pile)

Max Activating Token Index: 123

Text #16

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.5608. Min Act: -0.0000

Data Index: 839198 (The Pile)

Max Activating Token Index: 370

Text #17

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.5997. Min Act: -0.0000

Data Index: 88369 (The Pile)

Max Activating Token Index: 106

Text #18

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1614895 (The Pile)

Max Activating Token Index: 96

Text #19

Max Range: 0.8424. Min Range: -0.8424

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1217732 (The Pile)

Max Activating Token Index: 80