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

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

Neuron 2327 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.6429. Min Act: -0.0001

Data Index: 1222736 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.4105. Min Act: -0.0001

Data Index: 443500 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.4584. Min Act: -0.0001

Data Index: 591586 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.3000. Min Act: -0.0001

Data Index: 1122587 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.3383. Min Act: -0.0001

Data Index: 155263 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.2941. Min Act: -0.0001

Data Index: 414925 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.2445. Min Act: -0.0001

Data Index: 1350928 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.1810. Min Act: -0.0001

Data Index: 134066 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.1987. Min Act: -0.0001

Data Index: 307243 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.1049. Min Act: -0.0001

Data Index: 1026323 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.1162. Min Act: -0.0001

Data Index: 879073 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 1.6429. Min Range: -1.6429

Max Act: 0.9615. Min Act: -0.0001

Data Index: 1309427 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.1743. Min Act: -0.0001

Data Index: 27277 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 1.6429. Min Range: -1.6429

Max Act: 0.9485. Min Act: -0.0001

Data Index: 872920 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.1432. Min Act: -0.0001

Data Index: 613644 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.1912. Min Act: -0.0001

Data Index: 1126853 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 1.6429. Min Range: -1.6429

Max Act: 0.9718. Min Act: -0.0001

Data Index: 548021 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.0725. Min Act: -0.0001

Data Index: 98023 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.0961. Min Act: -0.0001

Data Index: 500642 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.0131. Min Act: -0.0001

Data Index: 1105558 (C4 (Web Text))

Max Activating Token Index: 1018