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

Dataset: The Pile

Neuron 3642 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1929. Min Range: -3.1929

Max Act: 3.1929. Min Act: -0.0000

Data Index: 521708 (The Pile)

Max Activating Token Index: 573

Text #1

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.9883. Min Act: -0.0000

Data Index: 157366 (The Pile)

Max Activating Token Index: 29

Text #2

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.9483. Min Act: -0.0000

Data Index: 1509342 (The Pile)

Max Activating Token Index: 29

Text #3

Max Range: 3.1929. Min Range: -3.1929

Max Act: 3.0060. Min Act: -0.0000

Data Index: 1727963 (The Pile)

Max Activating Token Index: 6

Text #4

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.7814. Min Act: -0.0000

Data Index: 1508512 (The Pile)

Max Activating Token Index: 26

Text #5

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.9015. Min Act: -0.0000

Data Index: 196429 (The Pile)

Max Activating Token Index: 765

Text #6

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.9043. Min Act: -0.0000

Data Index: 1176769 (The Pile)

Max Activating Token Index: 7

Text #7

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.6725. Min Act: -0.0000

Data Index: 531657 (The Pile)

Max Activating Token Index: 843

Text #8

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.6802. Min Act: -0.0000

Data Index: 149635 (The Pile)

Max Activating Token Index: 78

Text #9

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.6390. Min Act: -0.0000

Data Index: 1052245 (The Pile)

Max Activating Token Index: 8

Text #10

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.6420. Min Act: -0.0000

Data Index: 1145355 (The Pile)

Max Activating Token Index: 9

Text #11

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.7541. Min Act: -0.0000

Data Index: 1091009 (The Pile)

Max Activating Token Index: 139

Text #12

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.6067. Min Act: -0.0000

Data Index: 1399579 (The Pile)

Max Activating Token Index: 582

Text #13

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.6831. Min Act: -0.0000

Data Index: 633366 (The Pile)

Max Activating Token Index: 469

Text #14

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.6809. Min Act: -0.0000

Data Index: 89688 (The Pile)

Max Activating Token Index: 39

Text #15

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.6654. Min Act: -0.0000

Data Index: 1976957 (The Pile)

Max Activating Token Index: 9

Text #16

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.7983. Min Act: -0.0000

Data Index: 432353 (The Pile)

Max Activating Token Index: 36

Text #17

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.5282. Min Act: -0.0000

Data Index: 1557169 (The Pile)

Max Activating Token Index: 7

Text #18

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.5071. Min Act: -0.0000

Data Index: 261466 (The Pile)

Max Activating Token Index: 39

Text #19

Max Range: 3.1929. Min Range: -3.1929

Max Act: 2.6064. Min Act: -0.0000

Data Index: 1398283 (The Pile)

Max Activating Token Index: 8