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

Dataset: The Pile

Neuron 4390 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: 1.7331. Min Range: -1.7331

Max Act: 1.7331. Min Act: -0.0000

Data Index: 1774463 (The Pile)

Max Activating Token Index: 249

Text #1

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.5884. Min Act: -0.0000

Data Index: 719237 (The Pile)

Max Activating Token Index: 422

Text #2

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.3545. Min Act: -0.0000

Data Index: 1777037 (The Pile)

Max Activating Token Index: 56

Text #3

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.2900. Min Act: -0.0000

Data Index: 1825121 (The Pile)

Max Activating Token Index: 735

Text #4

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.4429. Min Act: -0.0000

Data Index: 345833 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.3651. Min Act: -0.0000

Data Index: 795212 (The Pile)

Max Activating Token Index: 833

Text #6

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.2073. Min Act: -0.0000

Data Index: 1544815 (The Pile)

Max Activating Token Index: 191

Text #7

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.0746. Min Act: -0.0000

Data Index: 230552 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 1.7331. Min Range: -1.7331

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1776451 (The Pile)

Max Activating Token Index: 139

Text #9

Max Range: 1.7331. Min Range: -1.7331

Max Act: 0.9636. Min Act: -0.0000

Data Index: 1613711 (The Pile)

Max Activating Token Index: 922

Text #10

Max Range: 1.7331. Min Range: -1.7331

Max Act: 0.9713. Min Act: -0.0000

Data Index: 1354279 (The Pile)

Max Activating Token Index: 649

Text #11

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.1815. Min Act: -0.0000

Data Index: 443852 (The Pile)

Max Activating Token Index: 757

Text #12

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.1500. Min Act: -0.0000

Data Index: 383029 (The Pile)

Max Activating Token Index: 867

Text #13

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.0993. Min Act: -0.0000

Data Index: 696685 (The Pile)

Max Activating Token Index: 854

Text #14

Max Range: 1.7331. Min Range: -1.7331

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1597401 (The Pile)

Max Activating Token Index: 20

Text #15

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.1066. Min Act: -0.0000

Data Index: 1003445 (The Pile)

Max Activating Token Index: 36

Text #16

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.0677. Min Act: -0.0000

Data Index: 1267666 (The Pile)

Max Activating Token Index: 22

Text #17

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.0962. Min Act: -0.0000

Data Index: 46603 (The Pile)

Max Activating Token Index: 598

Text #18

Max Range: 1.7331. Min Range: -1.7331

Max Act: 0.9983. Min Act: -0.0000

Data Index: 144184 (The Pile)

Max Activating Token Index: 384

Text #19

Max Range: 1.7331. Min Range: -1.7331

Max Act: 0.9843. Min Act: -0.0000

Data Index: 1589945 (The Pile)

Max Activating Token Index: 815