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

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

Neuron 4395 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.2352. Min Act: -0.0000

Data Index: 880163 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.1723. Min Act: -0.0000

Data Index: 103071 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.3979. Min Act: -0.0000

Data Index: 729051 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0026. Min Act: -0.0000

Data Index: 480982 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.1512. Min Act: -0.0000

Data Index: 926865 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.1776. Min Act: -0.0000

Data Index: 1174079 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.1588. Min Act: -0.0000

Data Index: 160175 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.1042. Min Act: -0.0000

Data Index: 571980 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.1755. Min Act: -0.0000

Data Index: 149339 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.1434. Min Act: -0.0000

Data Index: 22137 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0723. Min Act: -0.0000

Data Index: 73027 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0727. Min Act: -0.0000

Data Index: 453405 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 1.3979. Min Range: -1.3979

Max Act: 0.9841. Min Act: -0.0000

Data Index: 557106 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0864. Min Act: -0.0000

Data Index: 973045 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1231957 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 1.3979. Min Range: -1.3979

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1020446 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1095189 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0103. Min Act: -0.0000

Data Index: 769182 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 1.3979. Min Range: -1.3979

Max Act: 1.0609. Min Act: -0.0000

Data Index: 971754 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 1.3979. Min Range: -1.3979

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1063643 (C4 (Web Text))

Max Activating Token Index: 321