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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2649 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 6.2502. Min Range: -6.2502

Max Act: 6.2502. Min Act: -0.0000

Data Index: 733151 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 6.2502. Min Range: -6.2502

Max Act: 5.7014. Min Act: -0.0000

Data Index: 1121712 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 6.2502. Min Range: -6.2502

Max Act: 5.6606. Min Act: -0.0000

Data Index: 163048 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 6.2502. Min Range: -6.2502

Max Act: 5.8930. Min Act: -0.0000

Data Index: 819713 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 6.2502. Min Range: -6.2502

Max Act: 5.8759. Min Act: -0.0000

Data Index: 294511 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 6.2502. Min Range: -6.2502

Max Act: 5.5800. Min Act: -0.0000

Data Index: 208698 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 6.2502. Min Range: -6.2502

Max Act: 5.5406. Min Act: -0.0000

Data Index: 414085 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 6.2502. Min Range: -6.2502

Max Act: 5.5114. Min Act: -0.0000

Data Index: 372924 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 6.2502. Min Range: -6.2502

Max Act: 5.2124. Min Act: -0.0000

Data Index: 1100084 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 6.2502. Min Range: -6.2502

Max Act: 4.8418. Min Act: -0.0000

Data Index: 687967 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 6.2502. Min Range: -6.2502

Max Act: 4.8041. Min Act: -0.0000

Data Index: 812668 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 6.2502. Min Range: -6.2502

Max Act: 4.6374. Min Act: -0.0000

Data Index: 970670 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 6.2502. Min Range: -6.2502

Max Act: 4.7800. Min Act: -0.0000

Data Index: 423355 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 6.2502. Min Range: -6.2502

Max Act: 4.7185. Min Act: -0.0000

Data Index: 629073 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 6.2502. Min Range: -6.2502

Max Act: 4.7008. Min Act: -0.0000

Data Index: 679113 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 6.2502. Min Range: -6.2502

Max Act: 4.6694. Min Act: -0.0000

Data Index: 277904 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 6.2502. Min Range: -6.2502

Max Act: 4.6165. Min Act: -0.0000

Data Index: 922296 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 6.2502. Min Range: -6.2502

Max Act: 4.3500. Min Act: -0.0000

Data Index: 1022025 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 6.2502. Min Range: -6.2502

Max Act: 4.5088. Min Act: -0.0000

Data Index: 34910 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 6.2502. Min Range: -6.2502

Max Act: 4.4956. Min Act: -0.0000

Data Index: 621543 (C4 (Web Text))

Max Activating Token Index: 13