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

Dataset: The Pile

Neuron 3377 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: 0.9549. Min Range: -0.9549

Max Act: 0.9549. Min Act: -0.0000

Data Index: 80458 (The Pile)

Max Activating Token Index: 520

Text #1

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7102. Min Act: -0.0000

Data Index: 1018198 (The Pile)

Max Activating Token Index: 809

Text #2

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7965. Min Act: -0.0000

Data Index: 11556 (The Pile)

Max Activating Token Index: 215

Text #3

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1820521 (The Pile)

Max Activating Token Index: 774

Text #4

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1496712 (The Pile)

Max Activating Token Index: 240

Text #5

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6826. Min Act: -0.0000

Data Index: 114399 (The Pile)

Max Activating Token Index: 756

Text #6

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1493261 (The Pile)

Max Activating Token Index: 97

Text #7

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6469. Min Act: -0.0000

Data Index: 968827 (The Pile)

Max Activating Token Index: 719

Text #8

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6715. Min Act: -0.0000

Data Index: 127490 (The Pile)

Max Activating Token Index: 66

Text #9

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6560. Min Act: -0.0000

Data Index: 764062 (The Pile)

Max Activating Token Index: 924

Text #10

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1617654 (The Pile)

Max Activating Token Index: 717

Text #11

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.5814. Min Act: -0.0000

Data Index: 1253164 (The Pile)

Max Activating Token Index: 921

Text #12

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6133. Min Act: -0.0000

Data Index: 1180442 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6240. Min Act: -0.0000

Data Index: 933036 (The Pile)

Max Activating Token Index: 825

Text #14

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1163772 (The Pile)

Max Activating Token Index: 529

Text #15

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1416780 (The Pile)

Max Activating Token Index: 518

Text #16

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6184. Min Act: -0.0000

Data Index: 684733 (The Pile)

Max Activating Token Index: 941

Text #17

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6192. Min Act: -0.0000

Data Index: 412762 (The Pile)

Max Activating Token Index: 842

Text #18

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.6097. Min Act: -0.0000

Data Index: 344589 (The Pile)

Max Activating Token Index: 953

Text #19

Max Range: 0.9549. Min Range: -0.9549

Max Act: 0.5512. Min Act: -0.0000

Data Index: 723337 (The Pile)

Max Activating Token Index: 961