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

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

Neuron 1763 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.4527. Min Act: -0.0000

Data Index: 681310 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.4473. Min Act: -0.0001

Data Index: 1160881 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.4125. Min Act: -0.0000

Data Index: 663350 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.4221. Min Act: -0.0000

Data Index: 392370 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.4108. Min Act: -0.0001

Data Index: 506915 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.4011. Min Act: -0.0001

Data Index: 622802 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3777. Min Act: -0.0001

Data Index: 1006813 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3737. Min Act: -0.0001

Data Index: 324314 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1019283 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3838. Min Act: -0.0001

Data Index: 454039 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.4066. Min Act: -0.0000

Data Index: 878001 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3502. Min Act: -0.0001

Data Index: 286021 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3596. Min Act: -0.0001

Data Index: 1303668 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3166. Min Act: -0.0001

Data Index: 692338 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3577. Min Act: -0.0001

Data Index: 1325731 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3536. Min Act: -0.0001

Data Index: 65871 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3556. Min Act: -0.0001

Data Index: 1176997 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3449. Min Act: -0.0000

Data Index: 207249 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3238. Min Act: -0.0001

Data Index: 988229 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3673. Min Act: -0.0000

Data Index: 774059 (C4 (Web Text))

Max Activating Token Index: 736