Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3194 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.3240. Min Range: -2.3240

Max Act: 2.3240. Min Act: -0.0000

Data Index: 345812 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 2.3240. Min Range: -2.3240

Max Act: 2.0922. Min Act: -0.0000

Data Index: 686140 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 2.3240. Min Range: -2.3240

Max Act: 2.3173. Min Act: -0.0001

Data Index: 629688 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 2.3240. Min Range: -2.3240

Max Act: 2.1115. Min Act: -0.0000

Data Index: 254233 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 2.3240. Min Range: -2.3240

Max Act: 2.2501. Min Act: -0.0000

Data Index: 535414 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 2.3240. Min Range: -2.3240

Max Act: 2.0529. Min Act: -0.0000

Data Index: 714761 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 2.3240. Min Range: -2.3240

Max Act: 2.0892. Min Act: -0.0000

Data Index: 1022421 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 2.3240. Min Range: -2.3240

Max Act: 1.9005. Min Act: -0.0001

Data Index: 64130 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 2.3240. Min Range: -2.3240

Max Act: 2.1506. Min Act: -0.0000

Data Index: 1296316 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 2.3240. Min Range: -2.3240

Max Act: 1.9967. Min Act: -0.0001

Data Index: 275665 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 2.3240. Min Range: -2.3240

Max Act: 1.9676. Min Act: -0.0000

Data Index: 1296009 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 2.3240. Min Range: -2.3240

Max Act: 1.8856. Min Act: -0.0000

Data Index: 952176 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 2.3240. Min Range: -2.3240

Max Act: 1.8507. Min Act: -0.0000

Data Index: 1251915 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 2.3240. Min Range: -2.3240

Max Act: 1.9917. Min Act: -0.0000

Data Index: 1082541 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 2.3240. Min Range: -2.3240

Max Act: 1.8488. Min Act: -0.0000

Data Index: 739458 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 2.3240. Min Range: -2.3240

Max Act: 1.9108. Min Act: -0.0000

Data Index: 1353047 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 2.3240. Min Range: -2.3240

Max Act: 1.8016. Min Act: -0.0000

Data Index: 842705 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 2.3240. Min Range: -2.3240

Max Act: 1.7805. Min Act: -0.0001

Data Index: 494154 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 2.3240. Min Range: -2.3240

Max Act: 1.8639. Min Act: -0.0001

Data Index: 999751 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 2.3240. Min Range: -2.3240

Max Act: 1.8075. Min Act: -0.0000

Data Index: 622039 (C4 (Web Text))

Max Activating Token Index: 941