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

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

Neuron 5800 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: 1.3580. Min Range: -1.3580

Max Act: 1.3580. Min Act: -0.0000

Data Index: 1320132 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.9556. Min Act: -0.0000

Data Index: 723746 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.8146. Min Act: -0.0000

Data Index: 1341067 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.7741. Min Act: -0.0000

Data Index: 860933 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.7234. Min Act: -0.0000

Data Index: 392667 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1288893 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.7036. Min Act: -0.0000

Data Index: 561784 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1077714 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6471. Min Act: -0.0000

Data Index: 472187 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6580. Min Act: -0.0000

Data Index: 845851 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1190442 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6716. Min Act: -0.0000

Data Index: 611716 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6244. Min Act: -0.0000

Data Index: 185951 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6225. Min Act: -0.0000

Data Index: 604819 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6167. Min Act: -0.0000

Data Index: 580082 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6351. Min Act: -0.0000

Data Index: 187026 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6283. Min Act: -0.0000

Data Index: 453810 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.6260. Min Act: -0.0000

Data Index: 502748 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.5706. Min Act: -0.0000

Data Index: 372597 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 1.3580. Min Range: -1.3580

Max Act: 0.5888. Min Act: -0.0000

Data Index: 365297 (C4 (Web Text))

Max Activating Token Index: 615