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

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

Neuron 610 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: 0.3713. Min Range: -0.3713

Max Act: 0.3178. Min Act: -0.0000

Data Index: 878432 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3713. Min Act: -0.0000

Data Index: 87770 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1195912 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3491. Min Act: -0.0000

Data Index: 351934 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3582. Min Act: -0.0000

Data Index: 1050033 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3169. Min Act: -0.0000

Data Index: 506434 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3562. Min Act: -0.0000

Data Index: 517199 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1039143 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3352. Min Act: -0.0000

Data Index: 1218078 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1131731 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2979. Min Act: -0.0000

Data Index: 533304 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3016. Min Act: -0.0000

Data Index: 776346 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2899. Min Act: -0.0000

Data Index: 342927 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3127. Min Act: -0.0000

Data Index: 717682 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3055. Min Act: -0.0000

Data Index: 841047 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2946. Min Act: -0.0000

Data Index: 204965 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2835. Min Act: -0.0000

Data Index: 472262 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3223. Min Act: -0.0000

Data Index: 41410 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2664. Min Act: -0.0000

Data Index: 781467 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2811. Min Act: -0.0000

Data Index: 291291 (C4 (Web Text))

Max Activating Token Index: 478