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

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

Neuron 4714 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3659. Min Range: -2.3659

Max Act: 2.2860. Min Act: -0.0000

Data Index: 1152962 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 2.3659. Min Range: -2.3659

Max Act: 2.3659. Min Act: -0.0000

Data Index: 547137 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 2.3659. Min Range: -2.3659

Max Act: 2.1366. Min Act: -0.0000

Data Index: 457032 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 2.3659. Min Range: -2.3659

Max Act: 2.0451. Min Act: -0.0000

Data Index: 661226 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 2.3659. Min Range: -2.3659

Max Act: 1.9028. Min Act: -0.0000

Data Index: 50396 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 2.3659. Min Range: -2.3659

Max Act: 1.8875. Min Act: -0.0000

Data Index: 1186015 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 2.3659. Min Range: -2.3659

Max Act: 1.8747. Min Act: -0.0000

Data Index: 103207 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 2.3659. Min Range: -2.3659

Max Act: 1.9518. Min Act: -0.0000

Data Index: 498535 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 2.3659. Min Range: -2.3659

Max Act: 1.9563. Min Act: -0.0000

Data Index: 1242488 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 2.3659. Min Range: -2.3659

Max Act: 1.8351. Min Act: -0.0000

Data Index: 880056 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 2.3659. Min Range: -2.3659

Max Act: 1.9947. Min Act: -0.0000

Data Index: 737387 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 2.3659. Min Range: -2.3659

Max Act: 1.9591. Min Act: -0.0000

Data Index: 883130 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 2.3659. Min Range: -2.3659

Max Act: 1.8790. Min Act: -0.0000

Data Index: 1026142 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 2.3659. Min Range: -2.3659

Max Act: 1.9398. Min Act: -0.0000

Data Index: 949818 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 2.3659. Min Range: -2.3659

Max Act: 1.7262. Min Act: -0.0000

Data Index: 1065515 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 2.3659. Min Range: -2.3659

Max Act: 1.8083. Min Act: -0.0000

Data Index: 682874 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 2.3659. Min Range: -2.3659

Max Act: 1.7179. Min Act: -0.0000

Data Index: 832664 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 2.3659. Min Range: -2.3659

Max Act: 1.7735. Min Act: -0.0000

Data Index: 634988 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 2.3659. Min Range: -2.3659

Max Act: 1.7443. Min Act: -0.0000

Data Index: 391877 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 2.3659. Min Range: -2.3659

Max Act: 1.8209. Min Act: -0.0000

Data Index: 329664 (C4 (Web Text))

Max Activating Token Index: 415