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

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

Neuron 2613 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: 0.8602. Min Range: -0.8602

Max Act: 0.8602. Min Act: -0.0000

Data Index: 354971 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1122961 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.7229. Min Act: -0.0000

Data Index: 749036 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.6617. Min Act: -0.0000

Data Index: 264425 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.7007. Min Act: -0.0000

Data Index: 744590 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1134920 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1121222 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1284425 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1069679 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1139087 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1010476 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.6024. Min Act: -0.0000

Data Index: 654824 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.6121. Min Act: -0.0000

Data Index: 1170814 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.6108. Min Act: -0.0000

Data Index: 345823 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.6482. Min Act: -0.0000

Data Index: 203233 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1160764 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.6143. Min Act: -0.0000

Data Index: 592675 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.6108. Min Act: -0.0000

Data Index: 882831 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.6099. Min Act: -0.0000

Data Index: 56985 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.8602. Min Range: -0.8602

Max Act: 0.6269. Min Act: -0.0000

Data Index: 120342 (C4 (Web Text))

Max Activating Token Index: 285