Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 391 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.5540. Min Act: -0.0000

Data Index: 1113896 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6281. Min Act: -0.0000

Data Index: 1322820 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.5465. Min Act: -0.0000

Data Index: 1218765 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.5931. Min Act: -0.0000

Data Index: 92588 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.6802. Min Act: -0.0000

Data Index: 1135567 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.4867. Min Act: -0.0000

Data Index: 489036 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.3862. Min Act: -0.0000

Data Index: 1021856 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.5029. Min Act: -0.0000

Data Index: 788851 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.4821. Min Act: -0.0000

Data Index: 761929 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.5190. Min Act: -0.0000

Data Index: 734409 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.4322. Min Act: -0.0000

Data Index: 579861 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.4171. Min Act: -0.0000

Data Index: 1160408 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.3883. Min Act: -0.0000

Data Index: 283422 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.4051. Min Act: -0.0000

Data Index: 43910 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.4585. Min Act: -0.0000

Data Index: 666386 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.3579. Min Act: -0.0000

Data Index: 843115 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.2568. Min Act: -0.0000

Data Index: 298748 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.3338. Min Act: -0.0000

Data Index: 1196995 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.3002. Min Act: -0.0000

Data Index: 917524 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 1.6802. Min Range: -1.6802

Max Act: 1.3750. Min Act: -0.0000

Data Index: 145024 (C4 (Web Text))

Max Activating Token Index: 542