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

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

Neuron 804 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: 0.9818. Min Range: -0.9818

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1015876 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1009480 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.9301. Min Act: -0.0000

Data Index: 784101 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.8141. Min Act: -0.0000

Data Index: 461256 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.7637. Min Act: -0.0000

Data Index: 995818 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.7836. Min Act: -0.0000

Data Index: 1212931 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.7437. Min Act: 0.0000

Data Index: 1304077 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.7776. Min Act: -0.0000

Data Index: 150694 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.7447. Min Act: -0.0000

Data Index: 691030 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1222481 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.7251. Min Act: -0.0000

Data Index: 780247 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.7220. Min Act: -0.0000

Data Index: 765537 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.7130. Min Act: -0.0000

Data Index: 367733 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.7111. Min Act: -0.0000

Data Index: 444812 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.6978. Min Act: -0.0000

Data Index: 781993 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.6832. Min Act: -0.0000

Data Index: 60906 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.7092. Min Act: -0.0000

Data Index: 872902 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.6985. Min Act: -0.0000

Data Index: 809162 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.6671. Min Act: -0.0000

Data Index: 85478 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.9818. Min Range: -0.9818

Max Act: 0.6318. Min Act: 0.0000

Data Index: 939111 (C4 (Web Text))

Max Activating Token Index: 519