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

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

Neuron 3286 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: 0.9270. Min Range: -0.9270

Max Act: 0.9270. Min Act: -0.0000

Data Index: 1355840 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.7239. Min Act: -0.0000

Data Index: 587249 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1170844 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.6806. Min Act: -0.0000

Data Index: 1265055 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5999. Min Act: -0.0000

Data Index: 157624 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1324898 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.6494. Min Act: -0.0000

Data Index: 60367 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5651. Min Act: -0.0000

Data Index: 317872 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5590. Min Act: -0.0000

Data Index: 526127 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5384. Min Act: -0.0000

Data Index: 503528 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5927. Min Act: -0.0000

Data Index: 267157 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.6005. Min Act: -0.0000

Data Index: 397849 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5966. Min Act: -0.0000

Data Index: 706227 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5889. Min Act: -0.0000

Data Index: 993345 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1072232 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5562. Min Act: -0.0000

Data Index: 102897 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5350. Min Act: -0.0000

Data Index: 185486 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5871. Min Act: -0.0000

Data Index: 925127 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1065424 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.9270. Min Range: -0.9270

Max Act: 0.5791. Min Act: -0.0000

Data Index: 71682 (C4 (Web Text))

Max Activating Token Index: 158