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

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

Neuron 3725 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: 2.0677. Min Range: -2.0677

Max Act: 2.0677. Min Act: -0.0000

Data Index: 110414 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.9831. Min Act: -0.0000

Data Index: 1335339 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.8979. Min Act: -0.0000

Data Index: 45143 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.8363. Min Act: -0.0000

Data Index: 1108124 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.8205. Min Act: -0.0000

Data Index: 582170 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.9198. Min Act: -0.0000

Data Index: 576788 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.7189. Min Act: -0.0000

Data Index: 514135 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.6860. Min Act: -0.0000

Data Index: 112755 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.7585. Min Act: -0.0000

Data Index: 879300 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.6460. Min Act: -0.0000

Data Index: 1331396 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.6123. Min Act: -0.0000

Data Index: 605289 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.6236. Min Act: -0.0000

Data Index: 814780 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.5938. Min Act: -0.0000

Data Index: 530532 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.5906. Min Act: -0.0000

Data Index: 798132 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.6641. Min Act: -0.0000

Data Index: 370199 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.5427. Min Act: -0.0000

Data Index: 1106937 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.4600. Min Act: -0.0000

Data Index: 633125 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.6306. Min Act: -0.0000

Data Index: 460006 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.5323. Min Act: -0.0000

Data Index: 263880 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 2.0677. Min Range: -2.0677

Max Act: 1.4953. Min Act: -0.0000

Data Index: 1303358 (C4 (Web Text))

Max Activating Token Index: 204