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

Dataset: The Pile

Neuron 4010 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: 0.2398. Min Range: -0.2398

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1142051 (The Pile)

Max Activating Token Index: 290

Text #1

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2398. Min Act: -0.0000

Data Index: 187743 (The Pile)

Max Activating Token Index: 54

Text #2

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2279. Min Act: -0.0000

Data Index: 598983 (The Pile)

Max Activating Token Index: 228

Text #3

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2168. Min Act: -0.0000

Data Index: 383615 (The Pile)

Max Activating Token Index: 359

Text #4

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1828175 (The Pile)

Max Activating Token Index: 144

Text #5

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.2092. Min Act: -0.0000

Data Index: 1771104 (The Pile)

Max Activating Token Index: 579

Text #6

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1003428 (The Pile)

Max Activating Token Index: 951

Text #7

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1390918 (The Pile)

Max Activating Token Index: 112

Text #8

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1803. Min Act: -0.0000

Data Index: 1371211 (The Pile)

Max Activating Token Index: 30

Text #9

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1831. Min Act: -0.0000

Data Index: 1558921 (The Pile)

Max Activating Token Index: 193

Text #10

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1699. Min Act: -0.0000

Data Index: 339343 (The Pile)

Max Activating Token Index: 82

Text #11

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1747. Min Act: -0.0000

Data Index: 829930 (The Pile)

Max Activating Token Index: 300

Text #12

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1732314 (The Pile)

Max Activating Token Index: 105

Text #13

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1882937 (The Pile)

Max Activating Token Index: 578

Text #14

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1631. Min Act: -0.0000

Data Index: 1288544 (The Pile)

Max Activating Token Index: 181

Text #15

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1088750 (The Pile)

Max Activating Token Index: 62

Text #16

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1775. Min Act: -0.0000

Data Index: 776944 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1617. Min Act: -0.0000

Data Index: 774457 (The Pile)

Max Activating Token Index: 68

Text #18

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1004637 (The Pile)

Max Activating Token Index: 45

Text #19

Max Range: 0.2398. Min Range: -0.2398

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1982456 (The Pile)

Max Activating Token Index: 100