Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2717 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1348599 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.3143. Min Act: -0.0000

Data Index: 67508 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2889. Min Act: -0.0000

Data Index: 840195 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2850. Min Act: -0.0001

Data Index: 104711 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2752. Min Act: -0.0000

Data Index: 460765 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1264562 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2710. Min Act: -0.0000

Data Index: 403433 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2701. Min Act: -0.0000

Data Index: 46564 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2715. Min Act: -0.0000

Data Index: 964667 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2578. Min Act: -0.0000

Data Index: 728741 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2543. Min Act: -0.0001

Data Index: 1288944 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2622. Min Act: -0.0000

Data Index: 242980 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2503. Min Act: -0.0000

Data Index: 474260 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1184019 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2490. Min Act: -0.0000

Data Index: 1289502 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2575. Min Act: 0.0002

Data Index: 1189931 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1186526 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2575. Min Act: -0.0001

Data Index: 1159409 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2572. Min Act: 0.0000

Data Index: 1149822 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.3571. Min Range: -0.3571

Max Act: 0.2621. Min Act: 0.0002

Data Index: 749429 (C4 (Web Text))

Max Activating Token Index: 90