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

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

Neuron 3512 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.4817. Min Act: -0.0001

Data Index: 1215613 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3768. Min Act: -0.0001

Data Index: 1309461 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3180. Min Act: -0.0001

Data Index: 573719 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3200. Min Act: -0.0001

Data Index: 1262066 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3278. Min Act: -0.0001

Data Index: 1283832 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.3070. Min Act: -0.0001

Data Index: 644616 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.2442. Min Act: -0.0001

Data Index: 1231444 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.2839. Min Act: -0.0001

Data Index: 240373 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.2770. Min Act: -0.0001

Data Index: 507627 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.2869. Min Act: -0.0001

Data Index: 1060027 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.2876. Min Act: -0.0001

Data Index: 350029 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.2695. Min Act: -0.0001

Data Index: 1006941 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.2605. Min Act: -0.0001

Data Index: 1247103 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.2691. Min Act: -0.0001

Data Index: 1231480 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.2715. Min Act: -0.0001

Data Index: 845188 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.2789. Min Act: -0.0001

Data Index: 321351 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.2662. Min Act: -0.0001

Data Index: 1338396 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.2659. Min Act: -0.0001

Data Index: 943657 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.2507. Min Act: -0.0001

Data Index: 344566 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.4817. Min Range: -0.4817

Max Act: 0.2663. Min Act: -0.0001

Data Index: 704293 (C4 (Web Text))

Max Activating Token Index: 364