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

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

Neuron 4587 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: 3.8971. Min Range: -3.8971

Max Act: 3.7478. Min Act: -0.0000

Data Index: 91823 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 3.8971. Min Range: -3.8971

Max Act: 3.8971. Min Act: -0.0000

Data Index: 993831 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 3.8971. Min Range: -3.8971

Max Act: 3.6708. Min Act: -0.0000

Data Index: 381978 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 3.8971. Min Range: -3.8971

Max Act: 3.7720. Min Act: -0.0000

Data Index: 27318 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 3.8971. Min Range: -3.8971

Max Act: 3.3822. Min Act: -0.0000

Data Index: 697531 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 3.8971. Min Range: -3.8971

Max Act: 3.3786. Min Act: -0.0000

Data Index: 156444 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 3.8971. Min Range: -3.8971

Max Act: 2.9467. Min Act: -0.0000

Data Index: 797360 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 3.8971. Min Range: -3.8971

Max Act: 3.0793. Min Act: -0.0000

Data Index: 249027 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 3.8971. Min Range: -3.8971

Max Act: 3.1819. Min Act: -0.0000

Data Index: 573755 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 3.8971. Min Range: -3.8971

Max Act: 2.9786. Min Act: -0.0000

Data Index: 206296 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 3.8971. Min Range: -3.8971

Max Act: 3.1494. Min Act: -0.0000

Data Index: 839946 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 3.8971. Min Range: -3.8971

Max Act: 2.9213. Min Act: -0.0000

Data Index: 558524 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 3.8971. Min Range: -3.8971

Max Act: 2.9526. Min Act: -0.0000

Data Index: 69652 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 3.8971. Min Range: -3.8971

Max Act: 3.1585. Min Act: -0.0000

Data Index: 1122990 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 3.8971. Min Range: -3.8971

Max Act: 2.6999. Min Act: -0.0000

Data Index: 1336783 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 3.8971. Min Range: -3.8971

Max Act: 2.7068. Min Act: -0.0000

Data Index: 530896 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 3.8971. Min Range: -3.8971

Max Act: 2.9471. Min Act: -0.0000

Data Index: 928699 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 3.8971. Min Range: -3.8971

Max Act: 2.6468. Min Act: -0.0000

Data Index: 880450 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 3.8971. Min Range: -3.8971

Max Act: 2.9366. Min Act: -0.0000

Data Index: 75936 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 3.8971. Min Range: -3.8971

Max Act: 2.4707. Min Act: -0.0000

Data Index: 1283108 (C4 (Web Text))

Max Activating Token Index: 619