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

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

Neuron 337 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: 0.3672. Min Range: -0.3672

Max Act: 0.3672. Min Act: -0.0000

Data Index: 862718 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1124440 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1093144 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1057266 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.3162. Min Act: -0.0000

Data Index: 221731 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.3092. Min Act: -0.0000

Data Index: 726031 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2633. Min Act: -0.0000

Data Index: 243633 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2700. Min Act: -0.0000

Data Index: 437859 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2691. Min Act: -0.0000

Data Index: 919609 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2848. Min Act: -0.0000

Data Index: 299420 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1567982 (Python Code)

Max Activating Token Index: 421

Text #11

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2458. Min Act: -0.0000

Data Index: 938791 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2438. Min Act: -0.0000

Data Index: 436202 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2211. Min Act: -0.0000

Data Index: 1413445 (Python Code)

Max Activating Token Index: 756

Text #14

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2221. Min Act: -0.0000

Data Index: 356373 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2229. Min Act: -0.0000

Data Index: 346626 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2186. Min Act: -0.0000

Data Index: 603328 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2124. Min Act: -0.0000

Data Index: 296389 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1089134 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.3672. Min Range: -0.3672

Max Act: 0.1836. Min Act: -0.0000

Data Index: 11334 (C4 (Web Text))

Max Activating Token Index: 668