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

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

Neuron 4224 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: 1.0898. Min Range: -1.0898

Max Act: 1.0729. Min Act: -0.0000

Data Index: 12588 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 1.0898. Min Range: -1.0898

Max Act: 1.0898. Min Act: -0.0000

Data Index: 142985 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 1.0898. Min Range: -1.0898

Max Act: 1.0096. Min Act: -0.0000

Data Index: 1061725 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 1.0898. Min Range: -1.0898

Max Act: 1.0010. Min Act: -0.0000

Data Index: 498789 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.9959. Min Act: -0.0000

Data Index: 1170869 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.9676. Min Act: -0.0000

Data Index: 307372 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.9684. Min Act: -0.0000

Data Index: 572830 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.9254. Min Act: -0.0000

Data Index: 442844 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8918. Min Act: -0.0000

Data Index: 722384 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.9130. Min Act: -0.0000

Data Index: 375943 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.9645. Min Act: -0.0000

Data Index: 425947 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.9002. Min Act: -0.0000

Data Index: 11198 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1085969 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8744. Min Act: -0.0000

Data Index: 395222 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8680. Min Act: -0.0000

Data Index: 681196 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8417. Min Act: -0.0000

Data Index: 136125 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8535. Min Act: -0.0000

Data Index: 890881 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8152. Min Act: -0.0000

Data Index: 473576 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8437. Min Act: -0.0000

Data Index: 732436 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 1.0898. Min Range: -1.0898

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1206332 (C4 (Web Text))

Max Activating Token Index: 818