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

Dataset: The Pile

Neuron 4088 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: 0.5816. Min Range: -0.5816

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1831990 (The Pile)

Max Activating Token Index: 134

Text #1

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4652. Min Act: -0.0000

Data Index: 648876 (The Pile)

Max Activating Token Index: 731

Text #2

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.5816. Min Act: -0.0000

Data Index: 177269 (The Pile)

Max Activating Token Index: 214

Text #3

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1481122 (The Pile)

Max Activating Token Index: 169

Text #4

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1458291 (The Pile)

Max Activating Token Index: 56

Text #5

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1408304 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1489094 (The Pile)

Max Activating Token Index: 839

Text #7

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4486. Min Act: -0.0000

Data Index: 443502 (The Pile)

Max Activating Token Index: 225

Text #8

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.3730. Min Act: -0.0000

Data Index: 812442 (The Pile)

Max Activating Token Index: 338

Text #9

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1134046 (The Pile)

Max Activating Token Index: 349

Text #10

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.3266. Min Act: -0.0000

Data Index: 1520456 (The Pile)

Max Activating Token Index: 999

Text #11

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1656136 (The Pile)

Max Activating Token Index: 447

Text #12

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.3909. Min Act: -0.0000

Data Index: 287472 (The Pile)

Max Activating Token Index: 282

Text #13

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1137564 (The Pile)

Max Activating Token Index: 376

Text #14

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.3532. Min Act: -0.0000

Data Index: 381754 (The Pile)

Max Activating Token Index: 203

Text #15

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.3947. Min Act: -0.0000

Data Index: 1343045 (The Pile)

Max Activating Token Index: 251

Text #16

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1923824 (The Pile)

Max Activating Token Index: 140

Text #17

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.3382. Min Act: -0.0000

Data Index: 677859 (The Pile)

Max Activating Token Index: 387

Text #18

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.3026. Min Act: -0.0000

Data Index: 1161710 (The Pile)

Max Activating Token Index: 756

Text #19

Max Range: 0.5816. Min Range: -0.5816

Max Act: 0.3061. Min Act: -0.0000

Data Index: 660548 (The Pile)

Max Activating Token Index: 724