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

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

Neuron 3530 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3677. Min Act: -0.0000

Data Index: 284804 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1374332 (Python Code)

Max Activating Token Index: 660

Text #2

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3370. Min Act: -0.0000

Data Index: 701446 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3128. Min Act: -0.0000

Data Index: 739215 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3529. Min Act: -0.0000

Data Index: 980375 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3598. Min Act: -0.0000

Data Index: 326912 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3324. Min Act: -0.0000

Data Index: 1488642 (Python Code)

Max Activating Token Index: 601

Text #7

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.3099. Min Act: -0.0000

Data Index: 1035856 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2902. Min Act: -0.0000

Data Index: 292062 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2904. Min Act: -0.0000

Data Index: 852683 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2733. Min Act: -0.0000

Data Index: 331401 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1407847 (Python Code)

Max Activating Token Index: 425

Text #12

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2549. Min Act: -0.0000

Data Index: 274010 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1399764 (Python Code)

Max Activating Token Index: 311

Text #14

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1562588 (Python Code)

Max Activating Token Index: 48

Text #15

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2336. Min Act: -0.0000

Data Index: 659535 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1618067 (Python Code)

Max Activating Token Index: 880

Text #17

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2374. Min Act: -0.0000

Data Index: 62874 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1489344 (Python Code)

Max Activating Token Index: 946

Text #19

Max Range: 0.3677. Min Range: -0.3677

Max Act: 0.2139. Min Act: -0.0000

Data Index: 536841 (C4 (Web Text))

Max Activating Token Index: 579