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

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

Neuron 1700 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.8072. Min Act: -0.0000

Data Index: 466231 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.6012. Min Act: -0.0000

Data Index: 51868 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.5775. Min Act: -0.0000

Data Index: 783148 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.6569. Min Act: -0.0000

Data Index: 292299 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.6521. Min Act: -0.0000

Data Index: 275364 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.5488. Min Act: -0.0000

Data Index: 1070223 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.6339. Min Act: -0.0000

Data Index: 835691 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.5791. Min Act: -0.0000

Data Index: 266442 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.4860. Min Act: -0.0000

Data Index: 545013 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.4803. Min Act: -0.0000

Data Index: 1165899 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.4822. Min Act: -0.0000

Data Index: 613260 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.4132. Min Act: -0.0000

Data Index: 922504 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.4787. Min Act: -0.0000

Data Index: 87766 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.3838. Min Act: -0.0000

Data Index: 127670 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.3702. Min Act: -0.0000

Data Index: 339022 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.3360. Min Act: -0.0000

Data Index: 653906 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.2516. Min Act: -0.0000

Data Index: 631983 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.2262. Min Act: -0.0000

Data Index: 542900 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.2743. Min Act: -0.0000

Data Index: 1018089 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 1.8072. Min Range: -1.8072

Max Act: 1.2749. Min Act: -0.0000

Data Index: 432009 (C4 (Web Text))

Max Activating Token Index: 670