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

Dataset: The Pile

Neuron 4768 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: 3.9690. Min Range: -3.9690

Max Act: 3.8910. Min Act: -0.0000

Data Index: 1112517 (The Pile)

Max Activating Token Index: 62

Text #1

Max Range: 3.9690. Min Range: -3.9690

Max Act: 3.9690. Min Act: -0.0000

Data Index: 1028724 (The Pile)

Max Activating Token Index: 440

Text #2

Max Range: 3.9690. Min Range: -3.9690

Max Act: 3.7288. Min Act: -0.0000

Data Index: 1550561 (The Pile)

Max Activating Token Index: 96

Text #3

Max Range: 3.9690. Min Range: -3.9690

Max Act: 3.6415. Min Act: -0.0000

Data Index: 901250 (The Pile)

Max Activating Token Index: 7

Text #4

Max Range: 3.9690. Min Range: -3.9690

Max Act: 2.9542. Min Act: -0.0000

Data Index: 1200189 (The Pile)

Max Activating Token Index: 103

Text #5

Max Range: 3.9690. Min Range: -3.9690

Max Act: 3.6783. Min Act: -0.0000

Data Index: 40996 (The Pile)

Max Activating Token Index: 850

Text #6

Max Range: 3.9690. Min Range: -3.9690

Max Act: 3.1892. Min Act: -0.0000

Data Index: 1363371 (The Pile)

Max Activating Token Index: 56

Text #7

Max Range: 3.9690. Min Range: -3.9690

Max Act: 3.4486. Min Act: -0.0000

Data Index: 1412580 (The Pile)

Max Activating Token Index: 8

Text #8

Max Range: 3.9690. Min Range: -3.9690

Max Act: 3.4230. Min Act: -0.0000

Data Index: 254566 (The Pile)

Max Activating Token Index: 29

Text #9

Max Range: 3.9690. Min Range: -3.9690

Max Act: 3.5192. Min Act: -0.0000

Data Index: 1357072 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 3.9690. Min Range: -3.9690

Max Act: 2.3666. Min Act: -0.0000

Data Index: 1090102 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 3.9690. Min Range: -3.9690

Max Act: 3.0372. Min Act: -0.0000

Data Index: 34961 (The Pile)

Max Activating Token Index: 912

Text #12

Max Range: 3.9690. Min Range: -3.9690

Max Act: 3.6770. Min Act: -0.0000

Data Index: 378502 (The Pile)

Max Activating Token Index: 862

Text #13

Max Range: 3.9690. Min Range: -3.9690

Max Act: 3.3759. Min Act: -0.0000

Data Index: 1081054 (The Pile)

Max Activating Token Index: 59

Text #14

Max Range: 3.9690. Min Range: -3.9690

Max Act: 2.6124. Min Act: -0.0000

Data Index: 1247216 (The Pile)

Max Activating Token Index: 478

Text #15

Max Range: 3.9690. Min Range: -3.9690

Max Act: 3.3501. Min Act: -0.0000

Data Index: 99657 (The Pile)

Max Activating Token Index: 148

Text #16

Max Range: 3.9690. Min Range: -3.9690

Max Act: 3.1432. Min Act: -0.0000

Data Index: 671946 (The Pile)

Max Activating Token Index: 6

Text #17

Max Range: 3.9690. Min Range: -3.9690

Max Act: 3.1481. Min Act: -0.0000

Data Index: 717421 (The Pile)

Max Activating Token Index: 39

Text #18

Max Range: 3.9690. Min Range: -3.9690

Max Act: 2.9983. Min Act: -0.0000

Data Index: 1285919 (The Pile)

Max Activating Token Index: 9

Text #19

Max Range: 3.9690. Min Range: -3.9690

Max Act: 3.2522. Min Act: -0.0000

Data Index: 695146 (The Pile)

Max Activating Token Index: 28