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

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

Neuron 3896 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6111. Min Range: -2.6111

Max Act: 2.6111. Min Act: -0.0000

Data Index: 1157836 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 2.6111. Min Range: -2.6111

Max Act: 2.4903. Min Act: -0.0000

Data Index: 1512785 (Python Code)

Max Activating Token Index: 895

Text #2

Max Range: 2.6111. Min Range: -2.6111

Max Act: 2.4047. Min Act: -0.0000

Data Index: 499284 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 2.6111. Min Range: -2.6111

Max Act: 2.2786. Min Act: -0.0000

Data Index: 717115 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 2.6111. Min Range: -2.6111

Max Act: 2.2825. Min Act: -0.0000

Data Index: 612182 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 2.6111. Min Range: -2.6111

Max Act: 2.0878. Min Act: -0.0000

Data Index: 910260 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 2.6111. Min Range: -2.6111

Max Act: 2.1832. Min Act: -0.0000

Data Index: 1619760 (Python Code)

Max Activating Token Index: 600

Text #7

Max Range: 2.6111. Min Range: -2.6111

Max Act: 2.0374. Min Act: -0.0000

Data Index: 1333589 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 2.6111. Min Range: -2.6111

Max Act: 2.0315. Min Act: -0.0000

Data Index: 1101426 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 2.6111. Min Range: -2.6111

Max Act: 2.1355. Min Act: -0.0000

Data Index: 746028 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 2.6111. Min Range: -2.6111

Max Act: 1.8684. Min Act: -0.0000

Data Index: 1404613 (Python Code)

Max Activating Token Index: 799

Text #11

Max Range: 2.6111. Min Range: -2.6111

Max Act: 2.2131. Min Act: -0.0000

Data Index: 1509377 (Python Code)

Max Activating Token Index: 739

Text #12

Max Range: 2.6111. Min Range: -2.6111

Max Act: 1.9733. Min Act: -0.0000

Data Index: 1426082 (Python Code)

Max Activating Token Index: 623

Text #13

Max Range: 2.6111. Min Range: -2.6111

Max Act: 2.0922. Min Act: -0.0000

Data Index: 295966 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 2.6111. Min Range: -2.6111

Max Act: 2.0824. Min Act: -0.0000

Data Index: 477928 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 2.6111. Min Range: -2.6111

Max Act: 1.9402. Min Act: -0.0000

Data Index: 175441 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 2.6111. Min Range: -2.6111

Max Act: 2.0369. Min Act: -0.0000

Data Index: 638577 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 2.6111. Min Range: -2.6111

Max Act: 2.0184. Min Act: -0.0000

Data Index: 291588 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 2.6111. Min Range: -2.6111

Max Act: 2.0122. Min Act: -0.0000

Data Index: 292672 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 2.6111. Min Range: -2.6111

Max Act: 1.9187. Min Act: -0.0000

Data Index: 1028775 (C4 (Web Text))

Max Activating Token Index: 760