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

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

Neuron 656 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4415. Min Range: -2.4415

Max Act: 2.4415. Min Act: -0.0000

Data Index: 1349774 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 2.4415. Min Range: -2.4415

Max Act: 2.3045. Min Act: -0.0000

Data Index: 1241197 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 2.4415. Min Range: -2.4415

Max Act: 2.1693. Min Act: -0.0000

Data Index: 1305214 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 2.4415. Min Range: -2.4415

Max Act: 2.0682. Min Act: -0.0000

Data Index: 1352352 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 2.4415. Min Range: -2.4415

Max Act: 2.0622. Min Act: -0.0000

Data Index: 567045 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 2.4415. Min Range: -2.4415

Max Act: 2.0217. Min Act: -0.0000

Data Index: 973563 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 2.4415. Min Range: -2.4415

Max Act: 1.9243. Min Act: -0.0000

Data Index: 933898 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 2.4415. Min Range: -2.4415

Max Act: 1.9009. Min Act: -0.0000

Data Index: 472729 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 2.4415. Min Range: -2.4415

Max Act: 1.8169. Min Act: -0.0000

Data Index: 808603 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 2.4415. Min Range: -2.4415

Max Act: 1.7569. Min Act: -0.0000

Data Index: 519186 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 2.4415. Min Range: -2.4415

Max Act: 1.7382. Min Act: -0.0000

Data Index: 1078671 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 2.4415. Min Range: -2.4415

Max Act: 1.6939. Min Act: -0.0000

Data Index: 923653 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 2.4415. Min Range: -2.4415

Max Act: 1.6906. Min Act: -0.0000

Data Index: 492869 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 2.4415. Min Range: -2.4415

Max Act: 1.6849. Min Act: -0.0000

Data Index: 1180645 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 2.4415. Min Range: -2.4415

Max Act: 1.8622. Min Act: -0.0000

Data Index: 177404 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 2.4415. Min Range: -2.4415

Max Act: 1.6736. Min Act: -0.0000

Data Index: 984585 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 2.4415. Min Range: -2.4415

Max Act: 1.6665. Min Act: -0.0000

Data Index: 370237 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 2.4415. Min Range: -2.4415

Max Act: 1.7335. Min Act: -0.0000

Data Index: 1114371 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 2.4415. Min Range: -2.4415

Max Act: 1.6305. Min Act: -0.0000

Data Index: 1131831 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 2.4415. Min Range: -2.4415

Max Act: 1.8157. Min Act: -0.0000

Data Index: 1051007 (C4 (Web Text))

Max Activating Token Index: 533