Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2712 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1838. Min Range: -1.1838

Max Act: 1.1838. Min Act: -0.0001

Data Index: 983756 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.9664. Min Act: -0.0001

Data Index: 1076535 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.9687. Min Act: -0.0001

Data Index: 1187488 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.9107. Min Act: -0.0002

Data Index: 427425 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.7417. Min Act: -0.0001

Data Index: 1337301 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.8740. Min Act: -0.0001

Data Index: 157713 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.8999. Min Act: -0.0002

Data Index: 418741 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.8793. Min Act: -0.0002

Data Index: 30062 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.7265. Min Act: -0.0002

Data Index: 854123 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.7397. Min Act: -0.0001

Data Index: 175176 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.7206. Min Act: -0.0001

Data Index: 78995 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.7015. Min Act: -0.0001

Data Index: 1010565 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.7083. Min Act: -0.0001

Data Index: 662778 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.7649. Min Act: -0.0001

Data Index: 127277 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.7691. Min Act: -0.0001

Data Index: 550122 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.7599. Min Act: -0.0001

Data Index: 1044097 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.6465. Min Act: -0.0001

Data Index: 1263626 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.7179. Min Act: -0.0001

Data Index: 837528 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.6570. Min Act: -0.0001

Data Index: 1159573 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 1.1838. Min Range: -1.1838

Max Act: 0.6506. Min Act: -0.0001

Data Index: 836311 (C4 (Web Text))

Max Activating Token Index: 192