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

Dataset: The Pile

Neuron 232 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.6493. Min Act: -0.0000

Data Index: 427060 (The Pile)

Max Activating Token Index: 108

Text #1

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1967174 (The Pile)

Max Activating Token Index: 381

Text #2

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1621368 (The Pile)

Max Activating Token Index: 217

Text #3

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1284608 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1102636 (The Pile)

Max Activating Token Index: 919

Text #5

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1226851 (The Pile)

Max Activating Token Index: 997

Text #6

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5624. Min Act: 0.0000

Data Index: 1340243 (The Pile)

Max Activating Token Index: 225

Text #7

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5606. Min Act: -0.0000

Data Index: 175982 (The Pile)

Max Activating Token Index: 575

Text #8

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1370934 (The Pile)

Max Activating Token Index: 593

Text #9

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5096. Min Act: -0.0000

Data Index: 58027 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1547619 (The Pile)

Max Activating Token Index: 423

Text #11

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5133. Min Act: -0.0000

Data Index: 983713 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5329. Min Act: 0.0001

Data Index: 1436167 (The Pile)

Max Activating Token Index: 498

Text #13

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4955. Min Act: -0.0000

Data Index: 899315 (The Pile)

Max Activating Token Index: 296

Text #14

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1344135 (The Pile)

Max Activating Token Index: 130

Text #15

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5057. Min Act: -0.0000

Data Index: 106103 (The Pile)

Max Activating Token Index: 476

Text #16

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1176085 (The Pile)

Max Activating Token Index: 906

Text #17

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1680606 (The Pile)

Max Activating Token Index: 399

Text #18

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5018. Min Act: 0.0000

Data Index: 384880 (The Pile)

Max Activating Token Index: 951

Text #19

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4985. Min Act: -0.0000

Data Index: 201895 (The Pile)

Max Activating Token Index: 332