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

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

Neuron 794 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.5837. Min Act: -0.0000

Data Index: 456580 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.5939. Min Act: -0.0000

Data Index: 742091 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.6109. Min Act: -0.0000

Data Index: 145617 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.4219. Min Act: -0.0000

Data Index: 1198539 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.4294. Min Act: -0.0000

Data Index: 1048020 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.4370. Min Act: -0.0000

Data Index: 36320 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.3560. Min Act: -0.0000

Data Index: 724558 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.4675. Min Act: -0.0000

Data Index: 619935 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.4282. Min Act: -0.0000

Data Index: 501645 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.4717. Min Act: -0.0000

Data Index: 1349855 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.4772. Min Act: -0.0000

Data Index: 407299 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.3405. Min Act: -0.0000

Data Index: 1173661 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.2707. Min Act: -0.0000

Data Index: 968617 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.3792. Min Act: -0.0000

Data Index: 755873 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.3249. Min Act: -0.0000

Data Index: 820284 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.2797. Min Act: -0.0000

Data Index: 790295 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.3221. Min Act: -0.0000

Data Index: 82820 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.3441. Min Act: -0.0000

Data Index: 1291090 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.2298. Min Act: -0.0000

Data Index: 318355 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 1.6109. Min Range: -1.6109

Max Act: 1.2993. Min Act: -0.0000

Data Index: 781327 (C4 (Web Text))

Max Activating Token Index: 411