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

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

Neuron 1708 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0767. Min Range: -1.0767

Max Act: 1.0767. Min Act: -0.0000

Data Index: 471603 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.6639. Min Act: -0.0000

Data Index: 119872 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.6120. Min Act: -0.0000

Data Index: 929792 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.6047. Min Act: -0.0000

Data Index: 791202 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.5224. Min Act: -0.0000

Data Index: 822749 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.5458. Min Act: -0.0000

Data Index: 353289 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.5486. Min Act: -0.0000

Data Index: 1101857 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.5487. Min Act: -0.0000

Data Index: 587339 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.5275. Min Act: -0.0000

Data Index: 138171 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.5224. Min Act: 0.0000

Data Index: 537248 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.4983. Min Act: -0.0000

Data Index: 263963 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.4965. Min Act: -0.0000

Data Index: 736949 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.4971. Min Act: -0.0000

Data Index: 946330 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.4753. Min Act: -0.0000

Data Index: 501590 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1013236 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.5077. Min Act: 0.0000

Data Index: 808285 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.4569. Min Act: -0.0000

Data Index: 437626 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1226799 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.4469. Min Act: -0.0000

Data Index: 953324 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.4914. Min Act: -0.0000

Data Index: 684119 (C4 (Web Text))

Max Activating Token Index: 198