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

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

Neuron 4645 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9274. Min Range: -6.9274

Max Act: 6.9274. Min Act: -0.0000

Data Index: 938006 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 6.9274. Min Range: -6.9274

Max Act: 6.7722. Min Act: -0.0000

Data Index: 699361 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 6.9274. Min Range: -6.9274

Max Act: 6.4826. Min Act: -0.0000

Data Index: 978962 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 6.9274. Min Range: -6.9274

Max Act: 6.2798. Min Act: -0.0000

Data Index: 80146 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 6.9274. Min Range: -6.9274

Max Act: 5.3932. Min Act: -0.0000

Data Index: 498449 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 6.9274. Min Range: -6.9274

Max Act: 5.5357. Min Act: -0.0000

Data Index: 987285 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 6.9274. Min Range: -6.9274

Max Act: 4.8516. Min Act: -0.0000

Data Index: 1132219 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 6.9274. Min Range: -6.9274

Max Act: 4.6199. Min Act: -0.0000

Data Index: 358601 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 6.9274. Min Range: -6.9274

Max Act: 4.4484. Min Act: -0.0000

Data Index: 119110 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 6.9274. Min Range: -6.9274

Max Act: 4.6124. Min Act: -0.0000

Data Index: 883090 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 6.9274. Min Range: -6.9274

Max Act: 4.4189. Min Act: -0.0000

Data Index: 959744 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 6.9274. Min Range: -6.9274

Max Act: 4.4234. Min Act: -0.0000

Data Index: 996363 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 6.9274. Min Range: -6.9274

Max Act: 4.3790. Min Act: -0.0000

Data Index: 723278 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 6.9274. Min Range: -6.9274

Max Act: 4.3422. Min Act: -0.0000

Data Index: 958884 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 6.9274. Min Range: -6.9274

Max Act: 4.4314. Min Act: -0.0000

Data Index: 962599 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 6.9274. Min Range: -6.9274

Max Act: 4.4057. Min Act: -0.0000

Data Index: 119283 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 6.9274. Min Range: -6.9274

Max Act: 4.3690. Min Act: -0.0000

Data Index: 483389 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 6.9274. Min Range: -6.9274

Max Act: 4.3724. Min Act: -0.0000

Data Index: 1209520 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 6.9274. Min Range: -6.9274

Max Act: 4.1648. Min Act: -0.0000

Data Index: 1335700 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 6.9274. Min Range: -6.9274

Max Act: 4.3290. Min Act: -0.0000

Data Index: 29859 (C4 (Web Text))

Max Activating Token Index: 460