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

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

Neuron 3018 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.8976. Min Act: -0.0000

Data Index: 277864 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.9630. Min Act: -0.0000

Data Index: 1498321 (Python Code)

Max Activating Token Index: 991

Text #2

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.6283. Min Act: -0.0000

Data Index: 1651920 (Python Code)

Max Activating Token Index: 962

Text #3

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.8944. Min Act: -0.0000

Data Index: 1461698 (Python Code)

Max Activating Token Index: 972

Text #4

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.7868. Min Act: -0.0000

Data Index: 1310173 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.7766. Min Act: -0.0000

Data Index: 1624786 (Python Code)

Max Activating Token Index: 571

Text #6

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.7561. Min Act: -0.0000

Data Index: 1440595 (Python Code)

Max Activating Token Index: 120

Text #7

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.6441. Min Act: -0.0000

Data Index: 1109158 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.7334. Min Act: -0.0000

Data Index: 1289731 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.7127. Min Act: -0.0000

Data Index: 756824 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.6880. Min Act: -0.0000

Data Index: 993785 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.6393. Min Act: -0.0000

Data Index: 1638350 (Python Code)

Max Activating Token Index: 945

Text #12

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.6563. Min Act: -0.0000

Data Index: 381734 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.6132. Min Act: -0.0000

Data Index: 1579560 (Python Code)

Max Activating Token Index: 436

Text #14

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.6082. Min Act: -0.0000

Data Index: 939068 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.5499. Min Act: -0.0000

Data Index: 1464077 (Python Code)

Max Activating Token Index: 624

Text #16

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.5918. Min Act: -0.0000

Data Index: 1042796 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.5903. Min Act: -0.0000

Data Index: 1109426 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.5804. Min Act: -0.0000

Data Index: 482731 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 1.9630. Min Range: -1.9630

Max Act: 1.4511. Min Act: -0.0000

Data Index: 632960 (C4 (Web Text))

Max Activating Token Index: 728