Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4783 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.4989. Min Act: -0.0000

Data Index: 618600 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.3714. Min Act: -0.0000

Data Index: 322437 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.1681. Min Act: -0.0000

Data Index: 917825 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.1280. Min Act: -0.0000

Data Index: 83498 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.0633. Min Act: -0.0000

Data Index: 722489 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.1162. Min Act: -0.0000

Data Index: 78324 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.1446. Min Act: -0.0000

Data Index: 879182 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.0964. Min Act: -0.0000

Data Index: 238867 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.0237. Min Act: -0.0000

Data Index: 702191 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.1171. Min Act: -0.0000

Data Index: 862715 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.0689. Min Act: -0.0000

Data Index: 955530 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.0313. Min Act: -0.0000

Data Index: 846323 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.9798. Min Act: -0.0000

Data Index: 660879 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 1.4989. Min Range: -1.4989

Max Act: 1.1293. Min Act: -0.0000

Data Index: 1118764 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.8619. Min Act: -0.0000

Data Index: 701099 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.9676. Min Act: -0.0000

Data Index: 1143575 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.9253. Min Act: -0.0000

Data Index: 394633 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.9179. Min Act: -0.0000

Data Index: 314543 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.9516. Min Act: -0.0000

Data Index: 831845 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 1.4989. Min Range: -1.4989

Max Act: 0.9395. Min Act: -0.0000

Data Index: 459999 (C4 (Web Text))

Max Activating Token Index: 867