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

Dataset: The Pile

Neuron 4994 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: 3.4732. Min Range: -3.4732

Max Act: 3.3916. Min Act: -0.0000

Data Index: 487831 (The Pile)

Max Activating Token Index: 121

Text #1

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.4185. Min Act: -0.0000

Data Index: 19945 (The Pile)

Max Activating Token Index: 51

Text #2

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3929. Min Act: -0.0000

Data Index: 569643 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3112. Min Act: -0.0000

Data Index: 679724 (The Pile)

Max Activating Token Index: 109

Text #4

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3597. Min Act: -0.0000

Data Index: 1180004 (The Pile)

Max Activating Token Index: 175

Text #5

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.1683. Min Act: -0.0000

Data Index: 1440503 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3097. Min Act: -0.0000

Data Index: 477505 (The Pile)

Max Activating Token Index: 160

Text #7

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.2555. Min Act: -0.0000

Data Index: 1365888 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.2513. Min Act: -0.0000

Data Index: 1777458 (The Pile)

Max Activating Token Index: 435

Text #9

Max Range: 3.4732. Min Range: -3.4732

Max Act: 2.9406. Min Act: -0.0000

Data Index: 7856 (The Pile)

Max Activating Token Index: 41

Text #10

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.2107. Min Act: -0.0000

Data Index: 1878976 (The Pile)

Max Activating Token Index: 449

Text #11

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.1860. Min Act: -0.0000

Data Index: 563414 (The Pile)

Max Activating Token Index: 69

Text #12

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.2111. Min Act: -0.0000

Data Index: 411708 (The Pile)

Max Activating Token Index: 178

Text #13

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3366. Min Act: -0.0000

Data Index: 187366 (The Pile)

Max Activating Token Index: 41

Text #14

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3231. Min Act: -0.0000

Data Index: 1431426 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 3.4732. Min Range: -3.4732

Max Act: 2.8919. Min Act: -0.0000

Data Index: 372804 (The Pile)

Max Activating Token Index: 253

Text #16

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.0337. Min Act: -0.0000

Data Index: 210942 (The Pile)

Max Activating Token Index: 946

Text #17

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.0180. Min Act: -0.0000

Data Index: 1913384 (The Pile)

Max Activating Token Index: 30

Text #18

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3030. Min Act: -0.0000

Data Index: 51918 (The Pile)

Max Activating Token Index: 70

Text #19

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.4732. Min Act: -0.0000

Data Index: 561065 (The Pile)

Max Activating Token Index: 649