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

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

Neuron 2101 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: 8.7851. Min Range: -8.7851

Max Act: 8.7851. Min Act: -0.0000

Data Index: 763376 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 8.7851. Min Range: -8.7851

Max Act: 8.0576. Min Act: -0.0000

Data Index: 1041424 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 8.7851. Min Range: -8.7851

Max Act: 8.2340. Min Act: -0.0000

Data Index: 135822 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 8.7851. Min Range: -8.7851

Max Act: 8.0516. Min Act: -0.0000

Data Index: 734677 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 8.7851. Min Range: -8.7851

Max Act: 8.1273. Min Act: -0.0000

Data Index: 702963 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 8.7851. Min Range: -8.7851

Max Act: 7.9109. Min Act: -0.0000

Data Index: 1142812 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 8.7851. Min Range: -8.7851

Max Act: 7.8223. Min Act: -0.0000

Data Index: 492358 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 8.7851. Min Range: -8.7851

Max Act: 7.5934. Min Act: -0.0000

Data Index: 30517 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 8.7851. Min Range: -8.7851

Max Act: 7.9508. Min Act: -0.0000

Data Index: 683579 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 8.7851. Min Range: -8.7851

Max Act: 7.3162. Min Act: -0.0000

Data Index: 94779 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 8.7851. Min Range: -8.7851

Max Act: 7.3503. Min Act: -0.0000

Data Index: 355913 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 8.7851. Min Range: -8.7851

Max Act: 7.3341. Min Act: -0.0000

Data Index: 941331 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 8.7851. Min Range: -8.7851

Max Act: 7.2894. Min Act: -0.0000

Data Index: 85284 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 8.7851. Min Range: -8.7851

Max Act: 7.3072. Min Act: -0.0000

Data Index: 812549 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 8.7851. Min Range: -8.7851

Max Act: 7.2480. Min Act: -0.0000

Data Index: 569385 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 8.7851. Min Range: -8.7851

Max Act: 7.0280. Min Act: -0.0000

Data Index: 672425 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 8.7851. Min Range: -8.7851

Max Act: 6.6997. Min Act: -0.0000

Data Index: 49236 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 8.7851. Min Range: -8.7851

Max Act: 6.4260. Min Act: -0.0000

Data Index: 19336 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 8.7851. Min Range: -8.7851

Max Act: 5.9667. Min Act: -0.0000

Data Index: 649605 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 8.7851. Min Range: -8.7851

Max Act: 5.9045. Min Act: -0.0000

Data Index: 753861 (C4 (Web Text))

Max Activating Token Index: 418