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

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

Neuron 1458 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.3459. Min Act: -0.0000

Data Index: 737611 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2918. Min Act: -0.0000

Data Index: 460230 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2966. Min Act: -0.0000

Data Index: 613638 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1172130 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2837. Min Act: -0.0000

Data Index: 520449 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2848. Min Act: -0.0000

Data Index: 642537 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2805. Min Act: -0.0000

Data Index: 449333 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1112526 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.3201. Min Act: -0.0000

Data Index: 614918 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2823. Min Act: -0.0000

Data Index: 67332 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2695. Min Act: -0.0000

Data Index: 434037 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2686. Min Act: -0.0000

Data Index: 1234212 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2693. Min Act: -0.0000

Data Index: 902950 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2645. Min Act: -0.0000

Data Index: 868616 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2628. Min Act: -0.0000

Data Index: 179909 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2609. Min Act: -0.0000

Data Index: 546718 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2745. Min Act: -0.0000

Data Index: 604089 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2669. Min Act: -0.0000

Data Index: 821602 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1263155 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.3459. Min Range: -0.3459

Max Act: 0.2530. Min Act: -0.0000

Data Index: 363526 (C4 (Web Text))

Max Activating Token Index: 27