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

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

Neuron 3419 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2737. Min Act: -0.0001

Data Index: 953748 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2326. Min Act: -0.0001

Data Index: 776147 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.2453. Min Act: -0.0001

Data Index: 197820 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1870. Min Act: -0.0001

Data Index: 398072 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1856. Min Act: -0.0001

Data Index: 50351 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1860. Min Act: -0.0001

Data Index: 659067 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1665. Min Act: -0.0001

Data Index: 173983 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1748. Min Act: -0.0001

Data Index: 1016451 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1782. Min Act: -0.0001

Data Index: 392723 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1733. Min Act: -0.0001

Data Index: 198135 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1707. Min Act: -0.0001

Data Index: 1065193 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1600. Min Act: -0.0001

Data Index: 1182654 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1567. Min Act: -0.0001

Data Index: 218927 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1522. Min Act: -0.0001

Data Index: 799281 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1523. Min Act: -0.0001

Data Index: 369227 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1505. Min Act: -0.0001

Data Index: 938515 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1672. Min Act: -0.0001

Data Index: 90662 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1400. Min Act: -0.0001

Data Index: 826132 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1487. Min Act: -0.0001

Data Index: 1356240 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.2737. Min Range: -0.2737

Max Act: 0.1476. Min Act: -0.0001

Data Index: 754942 (C4 (Web Text))

Max Activating Token Index: 585