Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1464 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.8040. Min Act: -0.0003

Data Index: 699141 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.8311. Min Act: -0.0003

Data Index: 262763 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.9019. Min Act: -0.0003

Data Index: 560816 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.7989. Min Act: -0.0003

Data Index: 762942 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.7611. Min Act: -0.0003

Data Index: 124503 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.8671. Min Act: -0.0003

Data Index: 704550 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.8054. Min Act: -0.0003

Data Index: 710483 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.7633. Min Act: -0.0003

Data Index: 1304303 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.7850. Min Act: -0.0003

Data Index: 941825 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.7454. Min Act: -0.0003

Data Index: 665818 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.7997. Min Act: -0.0003

Data Index: 908351 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.7646. Min Act: -0.0003

Data Index: 474136 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.7187. Min Act: -0.0003

Data Index: 790080 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.7888. Min Act: -0.0003

Data Index: 727559 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.7763. Min Act: -0.0003

Data Index: 875408 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.7544. Min Act: -0.0003

Data Index: 181564 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.7499. Min Act: -0.0003

Data Index: 14300 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.7514. Min Act: -0.0003

Data Index: 176467 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.7790. Min Act: -0.0003

Data Index: 754643 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.9019. Min Range: -0.9019

Max Act: 0.6960. Min Act: -0.0003

Data Index: 214051 (C4 (Web Text))

Max Activating Token Index: 474