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

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

Neuron 4357 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6572. Min Range: -1.6572

Max Act: 1.6572. Min Act: -0.0000

Data Index: 836783 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 1.6572. Min Range: -1.6572

Max Act: 1.5540. Min Act: -0.0000

Data Index: 1155535 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 1.6572. Min Range: -1.6572

Max Act: 1.5983. Min Act: -0.0000

Data Index: 1326382 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 1.6572. Min Range: -1.6572

Max Act: 1.4682. Min Act: -0.0000

Data Index: 1181737 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 1.6572. Min Range: -1.6572

Max Act: 1.1788. Min Act: -0.0000

Data Index: 790425 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 1.6572. Min Range: -1.6572

Max Act: 0.9269. Min Act: -0.0000

Data Index: 1849 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 1.6572. Min Range: -1.6572

Max Act: 0.8793. Min Act: -0.0000

Data Index: 122560 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 1.6572. Min Range: -1.6572

Max Act: 0.8662. Min Act: -0.0000

Data Index: 533798 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 1.6572. Min Range: -1.6572

Max Act: 0.8217. Min Act: -0.0000

Data Index: 178288 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 1.6572. Min Range: -1.6572

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1156075 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 1.6572. Min Range: -1.6572

Max Act: 0.7448. Min Act: -0.0000

Data Index: 982484 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 1.6572. Min Range: -1.6572

Max Act: 0.7675. Min Act: -0.0000

Data Index: 1315759 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 1.6572. Min Range: -1.6572

Max Act: 0.7795. Min Act: -0.0000

Data Index: 913758 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 1.6572. Min Range: -1.6572

Max Act: 0.7840. Min Act: -0.0000

Data Index: 832197 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 1.6572. Min Range: -1.6572

Max Act: 0.7420. Min Act: -0.0000

Data Index: 1304265 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 1.6572. Min Range: -1.6572

Max Act: 0.7494. Min Act: -0.0000

Data Index: 1159846 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 1.6572. Min Range: -1.6572

Max Act: 0.7250. Min Act: -0.0000

Data Index: 96284 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 1.6572. Min Range: -1.6572

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1140067 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 1.6572. Min Range: -1.6572

Max Act: 0.7339. Min Act: -0.0000

Data Index: 810967 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 1.6572. Min Range: -1.6572

Max Act: 0.6868. Min Act: -0.0000

Data Index: 268523 (C4 (Web Text))

Max Activating Token Index: 177