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

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

Neuron 3632 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2997. Min Range: -1.2997

Max Act: 1.2997. Min Act: -0.0000

Data Index: 616469 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 1.2997. Min Range: -1.2997

Max Act: 1.0880. Min Act: -0.0001

Data Index: 895318 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.9936. Min Act: -0.0001

Data Index: 510381 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.9535. Min Act: -0.0001

Data Index: 715127 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.9548. Min Act: -0.0001

Data Index: 315242 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.9364. Min Act: -0.0000

Data Index: 570571 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8119. Min Act: -0.0001

Data Index: 1333354 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8767. Min Act: -0.0001

Data Index: 457650 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8317. Min Act: -0.0000

Data Index: 246154 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.7509. Min Act: -0.0000

Data Index: 635342 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.9211. Min Act: -0.0001

Data Index: 471193 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8492. Min Act: -0.0001

Data Index: 198259 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8126. Min Act: -0.0001

Data Index: 139669 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.7158. Min Act: -0.0001

Data Index: 173417 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8005. Min Act: -0.0000

Data Index: 500910 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8224. Min Act: -0.0001

Data Index: 327107 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.7863. Min Act: -0.0000

Data Index: 887438 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.8355. Min Act: -0.0001

Data Index: 625540 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.7602. Min Act: -0.0000

Data Index: 1141625 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 1.2997. Min Range: -1.2997

Max Act: 0.7078. Min Act: -0.0001

Data Index: 877314 (C4 (Web Text))

Max Activating Token Index: 318