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

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

Neuron 1031 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3255. Min Range: -1.3255

Max Act: 1.3255. Min Act: -0.0001

Data Index: 614576 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 1.3255. Min Range: -1.3255

Max Act: 1.1800. Min Act: -0.0001

Data Index: 123838 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 1.3255. Min Range: -1.3255

Max Act: 1.0681. Min Act: -0.0001

Data Index: 617831 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.9336. Min Act: -0.0001

Data Index: 206219 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.9901. Min Act: -0.0001

Data Index: 533559 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 1.3255. Min Range: -1.3255

Max Act: 1.0016. Min Act: -0.0001

Data Index: 580918 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.9297. Min Act: -0.0001

Data Index: 1179997 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.9832. Min Act: -0.0001

Data Index: 1154118 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.9498. Min Act: -0.0001

Data Index: 837191 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.9736. Min Act: -0.0001

Data Index: 1293179 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.8564. Min Act: -0.0001

Data Index: 380234 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.9516. Min Act: -0.0001

Data Index: 982223 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.8431. Min Act: -0.0001

Data Index: 944356 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.8336. Min Act: -0.0001

Data Index: 1239940 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.8837. Min Act: -0.0001

Data Index: 164623 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.8078. Min Act: -0.0001

Data Index: 428520 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.7949. Min Act: -0.0001

Data Index: 96639 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.8336. Min Act: -0.0001

Data Index: 542383 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.7214. Min Act: -0.0001

Data Index: 461755 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 1.3255. Min Range: -1.3255

Max Act: 0.7707. Min Act: -0.0001

Data Index: 34692 (C4 (Web Text))

Max Activating Token Index: 496