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

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

Neuron 3032 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.3868. Min Act: -0.0000

Data Index: 811424 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.3429. Min Act: -0.0000

Data Index: 370718 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.3092. Min Act: -0.0000

Data Index: 720364 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.3140. Min Act: -0.0000

Data Index: 720805 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2973. Min Act: -0.0000

Data Index: 874433 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2851. Min Act: -0.0000

Data Index: 1297809 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2951. Min Act: -0.0000

Data Index: 436521 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1535958 (Python Code)

Max Activating Token Index: 778

Text #8

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2628. Min Act: -0.0000

Data Index: 729768 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2776. Min Act: -0.0000

Data Index: 1194406 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2613. Min Act: -0.0000

Data Index: 390737 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2424. Min Act: 0.0000

Data Index: 1370139 (Python Code)

Max Activating Token Index: 249

Text #12

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2478. Min Act: -0.0000

Data Index: 899207 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2430. Min Act: -0.0000

Data Index: 238862 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2558. Min Act: -0.0000

Data Index: 246689 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2714. Min Act: -0.0000

Data Index: 906947 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2452. Min Act: -0.0000

Data Index: 1631737 (Python Code)

Max Activating Token Index: 863

Text #17

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1461634 (Python Code)

Max Activating Token Index: 608

Text #18

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2365. Min Act: -0.0000

Data Index: 1540225 (Python Code)

Max Activating Token Index: 908

Text #19

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1457172 (Python Code)

Max Activating Token Index: 816