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

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

Neuron 4793 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7343. Min Range: -2.7343

Max Act: 2.7343. Min Act: -0.0000

Data Index: 1082065 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 2.7343. Min Range: -2.7343

Max Act: 2.7078. Min Act: -0.0000

Data Index: 72837 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 2.7343. Min Range: -2.7343

Max Act: 2.5297. Min Act: -0.0000

Data Index: 37453 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 2.7343. Min Range: -2.7343

Max Act: 2.4254. Min Act: -0.0000

Data Index: 1206825 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 2.7343. Min Range: -2.7343

Max Act: 2.4045. Min Act: -0.0000

Data Index: 945007 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 2.7343. Min Range: -2.7343

Max Act: 2.1037. Min Act: -0.0000

Data Index: 765995 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 2.7343. Min Range: -2.7343

Max Act: 1.9855. Min Act: -0.0000

Data Index: 472687 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 2.7343. Min Range: -2.7343

Max Act: 1.9974. Min Act: -0.0000

Data Index: 351386 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 2.7343. Min Range: -2.7343

Max Act: 1.9135. Min Act: -0.0000

Data Index: 969851 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 2.7343. Min Range: -2.7343

Max Act: 2.0297. Min Act: -0.0000

Data Index: 934425 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 2.7343. Min Range: -2.7343

Max Act: 1.7593. Min Act: -0.0000

Data Index: 1118939 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 2.7343. Min Range: -2.7343

Max Act: 1.9534. Min Act: -0.0000

Data Index: 364370 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 2.7343. Min Range: -2.7343

Max Act: 1.7082. Min Act: -0.0000

Data Index: 714008 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 2.7343. Min Range: -2.7343

Max Act: 1.7867. Min Act: -0.0000

Data Index: 954775 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 2.7343. Min Range: -2.7343

Max Act: 1.7834. Min Act: -0.0000

Data Index: 1174733 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 2.7343. Min Range: -2.7343

Max Act: 1.7837. Min Act: -0.0000

Data Index: 87305 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 2.7343. Min Range: -2.7343

Max Act: 1.7537. Min Act: -0.0000

Data Index: 711955 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 2.7343. Min Range: -2.7343

Max Act: 1.5115. Min Act: -0.0000

Data Index: 206335 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 2.7343. Min Range: -2.7343

Max Act: 1.6828. Min Act: -0.0000

Data Index: 1164234 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 2.7343. Min Range: -2.7343

Max Act: 1.6564. Min Act: -0.0000

Data Index: 32210 (C4 (Web Text))

Max Activating Token Index: 314