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

Dataset: The Pile

Neuron 2565 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1196768 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5290. Min Act: -0.0000

Data Index: 300067 (The Pile)

Max Activating Token Index: 142

Text #2

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4508. Min Act: -0.0000

Data Index: 458573 (The Pile)

Max Activating Token Index: 191

Text #3

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4343. Min Act: -0.0000

Data Index: 360967 (The Pile)

Max Activating Token Index: 77

Text #4

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1845632 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1365607 (The Pile)

Max Activating Token Index: 20

Text #6

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1524954 (The Pile)

Max Activating Token Index: 8

Text #7

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1989283 (The Pile)

Max Activating Token Index: 7

Text #8

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1917609 (The Pile)

Max Activating Token Index: 21

Text #9

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3651. Min Act: -0.0000

Data Index: 326649 (The Pile)

Max Activating Token Index: 129

Text #10

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1842493 (The Pile)

Max Activating Token Index: 655

Text #11

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1770666 (The Pile)

Max Activating Token Index: 745

Text #12

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3705. Min Act: -0.0000

Data Index: 916102 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3678. Min Act: -0.0000

Data Index: 835787 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3534. Min Act: -0.0000

Data Index: 1470760 (The Pile)

Max Activating Token Index: 116

Text #15

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3699. Min Act: -0.0000

Data Index: 989237 (The Pile)

Max Activating Token Index: 81

Text #16

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3495. Min Act: -0.0000

Data Index: 1414980 (The Pile)

Max Activating Token Index: 7

Text #17

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1747216 (The Pile)

Max Activating Token Index: 857

Text #18

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1531334 (The Pile)

Max Activating Token Index: 363

Text #19

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1071379 (The Pile)

Max Activating Token Index: 570