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

Dataset: The Pile

Neuron 70 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1391. Min Range: -1.1391

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1353672 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1842055 (The Pile)

Max Activating Token Index: 828

Text #2

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.9371. Min Act: -0.0000

Data Index: 906483 (The Pile)

Max Activating Token Index: 890

Text #3

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1403931 (The Pile)

Max Activating Token Index: 903

Text #4

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8444. Min Act: 0.0000

Data Index: 1001495 (The Pile)

Max Activating Token Index: 807

Text #5

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8402. Min Act: -0.0000

Data Index: 697252 (The Pile)

Max Activating Token Index: 592

Text #6

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8247. Min Act: -0.0000

Data Index: 198677 (The Pile)

Max Activating Token Index: 772

Text #7

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8929. Min Act: -0.0000

Data Index: 1090835 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7797. Min Act: -0.0000

Data Index: 144568 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7846. Min Act: 0.0000

Data Index: 436265 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8307. Min Act: -0.0000

Data Index: 789192 (The Pile)

Max Activating Token Index: 584

Text #11

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7963. Min Act: -0.0000

Data Index: 698546 (The Pile)

Max Activating Token Index: 204

Text #12

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7509. Min Act: -0.0000

Data Index: 367548 (The Pile)

Max Activating Token Index: 1018

Text #13

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1228081 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7699. Min Act: -0.0000

Data Index: 631344 (The Pile)

Max Activating Token Index: 882

Text #15

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7785. Min Act: -0.0000

Data Index: 1021097 (The Pile)

Max Activating Token Index: 432

Text #16

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7759. Min Act: -0.0000

Data Index: 834802 (The Pile)

Max Activating Token Index: 255

Text #17

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7724. Min Act: -0.0000

Data Index: 1408217 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1295837 (The Pile)

Max Activating Token Index: 103

Text #19

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7661. Min Act: 0.0000

Data Index: 1618050 (The Pile)

Max Activating Token Index: 489