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

Dataset: The Pile

Neuron 2260 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7976. Min Act: -0.0000

Data Index: 119200 (The Pile)

Max Activating Token Index: 111

Text #1

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7839. Min Act: -0.0000

Data Index: 676667 (The Pile)

Max Activating Token Index: 358

Text #2

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6565. Min Act: -0.0000

Data Index: 351908 (The Pile)

Max Activating Token Index: 107

Text #3

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7064. Min Act: 0.0000

Data Index: 1328931 (The Pile)

Max Activating Token Index: 875

Text #4

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6857. Min Act: 0.0000

Data Index: 1391545 (The Pile)

Max Activating Token Index: 55

Text #5

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6565. Min Act: -0.0000

Data Index: 826489 (The Pile)

Max Activating Token Index: 949

Text #6

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6439. Min Act: 0.0000

Data Index: 293152 (The Pile)

Max Activating Token Index: 140

Text #7

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6475. Min Act: -0.0000

Data Index: 1943426 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1653261 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1986428 (The Pile)

Max Activating Token Index: 170

Text #10

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6213. Min Act: -0.0000

Data Index: 232922 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6107. Min Act: -0.0000

Data Index: 503733 (The Pile)

Max Activating Token Index: 616

Text #12

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6124. Min Act: 0.0000

Data Index: 552780 (The Pile)

Max Activating Token Index: 81

Text #13

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1842122 (The Pile)

Max Activating Token Index: 790

Text #14

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1251494 (The Pile)

Max Activating Token Index: 305

Text #15

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6148. Min Act: -0.0000

Data Index: 284864 (The Pile)

Max Activating Token Index: 73

Text #16

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.5959. Min Act: -0.0000

Data Index: 171351 (The Pile)

Max Activating Token Index: 99

Text #17

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.5621. Min Act: -0.0000

Data Index: 954483 (The Pile)

Max Activating Token Index: 540

Text #18

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.5958. Min Act: -0.0000

Data Index: 935980 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1555197 (The Pile)

Max Activating Token Index: 138