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

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

Neuron 448 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7901. Min Range: -2.7901

Max Act: 2.7479. Min Act: -0.0000

Data Index: 830826 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 2.7901. Min Range: -2.7901

Max Act: 2.7901. Min Act: -0.0000

Data Index: 749450 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 2.7901. Min Range: -2.7901

Max Act: 2.5785. Min Act: -0.0000

Data Index: 1141062 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 2.7901. Min Range: -2.7901

Max Act: 2.7650. Min Act: -0.0000

Data Index: 981136 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 2.7901. Min Range: -2.7901

Max Act: 2.6875. Min Act: 0.0000

Data Index: 1148746 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 2.7901. Min Range: -2.7901

Max Act: 2.4780. Min Act: -0.0000

Data Index: 270699 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 2.7901. Min Range: -2.7901

Max Act: 2.4202. Min Act: -0.0000

Data Index: 199880 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 2.7901. Min Range: -2.7901

Max Act: 2.4331. Min Act: -0.0000

Data Index: 161855 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 2.7901. Min Range: -2.7901

Max Act: 2.1671. Min Act: -0.0000

Data Index: 803730 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 2.7901. Min Range: -2.7901

Max Act: 2.2858. Min Act: -0.0000

Data Index: 937699 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 2.7901. Min Range: -2.7901

Max Act: 2.2942. Min Act: -0.0000

Data Index: 596149 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 2.7901. Min Range: -2.7901

Max Act: 2.1417. Min Act: -0.0000

Data Index: 786676 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 2.7901. Min Range: -2.7901

Max Act: 2.1392. Min Act: -0.0000

Data Index: 592899 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 2.7901. Min Range: -2.7901

Max Act: 2.1057. Min Act: -0.0000

Data Index: 1108167 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 2.7901. Min Range: -2.7901

Max Act: 1.8701. Min Act: -0.0000

Data Index: 20539 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 2.7901. Min Range: -2.7901

Max Act: 1.9517. Min Act: -0.0000

Data Index: 121727 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 2.7901. Min Range: -2.7901

Max Act: 1.9876. Min Act: -0.0000

Data Index: 684165 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 2.7901. Min Range: -2.7901

Max Act: 1.8809. Min Act: -0.0000

Data Index: 555368 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 2.7901. Min Range: -2.7901

Max Act: 1.9378. Min Act: -0.0000

Data Index: 1176614 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 2.7901. Min Range: -2.7901

Max Act: 1.9269. Min Act: -0.0000

Data Index: 1158391 (C4 (Web Text))

Max Activating Token Index: 268