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

Dataset: The Pile

Neuron 34 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.6359. Min Act: -0.0000

Data Index: 630317 (The Pile)

Max Activating Token Index: 665

Text #1

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.5604. Min Act: -0.0000

Data Index: 829400 (The Pile)

Max Activating Token Index: 302

Text #2

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.4679. Min Act: -0.0000

Data Index: 1165192 (The Pile)

Max Activating Token Index: 107

Text #3

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.2940. Min Act: -0.0000

Data Index: 1285111 (The Pile)

Max Activating Token Index: 663

Text #4

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.9871. Min Act: -0.0000

Data Index: 1427302 (The Pile)

Max Activating Token Index: 940

Text #5

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.1915. Min Act: -0.0000

Data Index: 1575251 (The Pile)

Max Activating Token Index: 49

Text #6

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.3048. Min Act: -0.0000

Data Index: 1657636 (The Pile)

Max Activating Token Index: 785

Text #7

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.1073. Min Act: -0.0000

Data Index: 1675497 (The Pile)

Max Activating Token Index: 748

Text #8

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.0480. Min Act: -0.0000

Data Index: 34284 (The Pile)

Max Activating Token Index: 725

Text #9

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.1779. Min Act: -0.0000

Data Index: 795436 (The Pile)

Max Activating Token Index: 831

Text #10

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.3356. Min Act: -0.0000

Data Index: 156629 (The Pile)

Max Activating Token Index: 201

Text #11

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.1579. Min Act: -0.0000

Data Index: 1563979 (The Pile)

Max Activating Token Index: 502

Text #12

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.0035. Min Act: -0.0000

Data Index: 1205867 (The Pile)

Max Activating Token Index: 778

Text #13

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.9705. Min Act: -0.0000

Data Index: 946852 (The Pile)

Max Activating Token Index: 500

Text #14

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.9802. Min Act: -0.0000

Data Index: 835489 (The Pile)

Max Activating Token Index: 738

Text #15

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.9305. Min Act: -0.0000

Data Index: 460525 (The Pile)

Max Activating Token Index: 133

Text #16

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.0458. Min Act: -0.0000

Data Index: 860179 (The Pile)

Max Activating Token Index: 856

Text #17

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.2439. Min Act: -0.0000

Data Index: 1551983 (The Pile)

Max Activating Token Index: 876

Text #18

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.8545. Min Act: -0.0000

Data Index: 737387 (The Pile)

Max Activating Token Index: 853

Text #19

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.9800. Min Act: -0.0000

Data Index: 1338405 (The Pile)

Max Activating Token Index: 258