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

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

Neuron 3694 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9295. Min Range: -2.9295

Max Act: 2.9295. Min Act: -0.0001

Data Index: 1326381 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 2.9295. Min Range: -2.9295

Max Act: 2.2630. Min Act: -0.0000

Data Index: 504226 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 2.9295. Min Range: -2.9295

Max Act: 2.3497. Min Act: -0.0000

Data Index: 569665 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 2.9295. Min Range: -2.9295

Max Act: 2.2247. Min Act: -0.0000

Data Index: 358775 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 2.9295. Min Range: -2.9295

Max Act: 2.2043. Min Act: -0.0000

Data Index: 1155450 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 2.9295. Min Range: -2.9295

Max Act: 2.2003. Min Act: -0.0001

Data Index: 655655 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 2.9295. Min Range: -2.9295

Max Act: 2.2103. Min Act: -0.0000

Data Index: 1063704 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 2.9295. Min Range: -2.9295

Max Act: 2.1765. Min Act: -0.0000

Data Index: 1274792 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 2.9295. Min Range: -2.9295

Max Act: 2.1812. Min Act: -0.0000

Data Index: 670097 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 2.9295. Min Range: -2.9295

Max Act: 2.0403. Min Act: -0.0000

Data Index: 754232 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 2.9295. Min Range: -2.9295

Max Act: 1.9413. Min Act: -0.0001

Data Index: 400411 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 2.9295. Min Range: -2.9295

Max Act: 2.2764. Min Act: -0.0000

Data Index: 1301420 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 2.9295. Min Range: -2.9295

Max Act: 1.8955. Min Act: -0.0000

Data Index: 1009335 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 2.9295. Min Range: -2.9295

Max Act: 2.0954. Min Act: -0.0000

Data Index: 705665 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 2.9295. Min Range: -2.9295

Max Act: 2.2223. Min Act: -0.0000

Data Index: 261796 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 2.9295. Min Range: -2.9295

Max Act: 1.8704. Min Act: -0.0000

Data Index: 919067 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 2.9295. Min Range: -2.9295

Max Act: 2.0436. Min Act: -0.0000

Data Index: 197406 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 2.9295. Min Range: -2.9295

Max Act: 1.9549. Min Act: -0.0001

Data Index: 1187379 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 2.9295. Min Range: -2.9295

Max Act: 2.0238. Min Act: -0.0000

Data Index: 308809 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 2.9295. Min Range: -2.9295

Max Act: 1.7206. Min Act: -0.0000

Data Index: 814241 (C4 (Web Text))

Max Activating Token Index: 846