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

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

Neuron 1040 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.8783. Min Act: -0.0000

Data Index: 27012 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.7496. Min Act: -0.0000

Data Index: 18613 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.7725. Min Act: -0.0000

Data Index: 481951 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.7585. Min Act: -0.0000

Data Index: 773557 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.7391. Min Act: -0.0000

Data Index: 1099075 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.8209. Min Act: -0.0000

Data Index: 905628 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.8153. Min Act: -0.0000

Data Index: 394016 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.6101. Min Act: -0.0000

Data Index: 414417 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.7065. Min Act: -0.0000

Data Index: 1012433 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.6969. Min Act: -0.0000

Data Index: 924360 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.5731. Min Act: -0.0000

Data Index: 808827 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.5621. Min Act: -0.0000

Data Index: 673354 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.5340. Min Act: -0.0000

Data Index: 946609 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.4326. Min Act: -0.0000

Data Index: 1244471 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.6194. Min Act: -0.0000

Data Index: 908301 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.7135. Min Act: -0.0000

Data Index: 1199779 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.5198. Min Act: -0.0000

Data Index: 350729 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.5094. Min Act: -0.0000

Data Index: 327885 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.4930. Min Act: -0.0000

Data Index: 71142 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 1.8783. Min Range: -1.8783

Max Act: 1.6690. Min Act: -0.0000

Data Index: 76304 (C4 (Web Text))

Max Activating Token Index: 577