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

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

Neuron 3687 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.8679. Min Act: -0.0001

Data Index: 362169 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.7640. Min Act: -0.0001

Data Index: 539676 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.7773. Min Act: -0.0001

Data Index: 846526 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.7103. Min Act: -0.0001

Data Index: 106690 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6758. Min Act: -0.0001

Data Index: 792293 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6955. Min Act: -0.0001

Data Index: 223139 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6605. Min Act: -0.0001

Data Index: 398282 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6800. Min Act: -0.0001

Data Index: 1172907 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6468. Min Act: -0.0001

Data Index: 244425 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6232. Min Act: -0.0001

Data Index: 961631 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6656. Min Act: -0.0001

Data Index: 566730 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6541. Min Act: -0.0001

Data Index: 1359269 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6814. Min Act: -0.0001

Data Index: 1051563 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6804. Min Act: -0.0001

Data Index: 1147924 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6578. Min Act: -0.0001

Data Index: 798782 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6539. Min Act: -0.0001

Data Index: 800336 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6704. Min Act: -0.0001

Data Index: 1142410 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6138. Min Act: -0.0001

Data Index: 1053936 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.5877. Min Act: -0.0001

Data Index: 723432 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6299. Min Act: -0.0001

Data Index: 834130 (C4 (Web Text))

Max Activating Token Index: 389