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

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

Neuron 1086 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: 1.5210. Min Range: -1.5210

Max Act: 1.5210. Min Act: -0.0000

Data Index: 309409 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.3779. Min Act: -0.0000

Data Index: 876984 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.2315. Min Act: -0.0000

Data Index: 1068133 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.2853. Min Act: -0.0000

Data Index: 609136 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.2271. Min Act: -0.0000

Data Index: 764185 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.2061. Min Act: -0.0000

Data Index: 869324 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.2737. Min Act: -0.0000

Data Index: 131391 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0937. Min Act: -0.0000

Data Index: 586451 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1521. Min Act: -0.0000

Data Index: 923261 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.2160. Min Act: -0.0000

Data Index: 564780 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1923. Min Act: -0.0000

Data Index: 119822 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1934. Min Act: -0.0000

Data Index: 231576 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0600. Min Act: -0.0000

Data Index: 1317742 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0661. Min Act: -0.0000

Data Index: 1443371 (Python Code)

Max Activating Token Index: 791

Text #14

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0487. Min Act: -0.0000

Data Index: 21037 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0446. Min Act: -0.0000

Data Index: 23051 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.1470. Min Act: -0.0000

Data Index: 683215 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0645. Min Act: -0.0000

Data Index: 476797 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0574. Min Act: -0.0000

Data Index: 1262592 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 1.5210. Min Range: -1.5210

Max Act: 1.0565. Min Act: -0.0000

Data Index: 294054 (C4 (Web Text))

Max Activating Token Index: 988