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

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

Neuron 4318 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.7707. Min Act: -0.0002

Data Index: 1239530 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.7121. Min Act: -0.0002

Data Index: 832883 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.6878. Min Act: -0.0002

Data Index: 414597 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.6776. Min Act: -0.0002

Data Index: 1292656 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.5949. Min Act: -0.0002

Data Index: 1335221 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.5949. Min Act: -0.0002

Data Index: 706630 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.5949. Min Act: -0.0003

Data Index: 138339 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.6085. Min Act: -0.0002

Data Index: 726201 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.5981. Min Act: -0.0002

Data Index: 71122 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.5636. Min Act: -0.0002

Data Index: 234136 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.6347. Min Act: -0.0002

Data Index: 916989 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.5664. Min Act: -0.0002

Data Index: 556740 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.5736. Min Act: -0.0003

Data Index: 553188 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.5513. Min Act: -0.0002

Data Index: 643056 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.5423. Min Act: -0.0002

Data Index: 861584 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.5660. Min Act: -0.0002

Data Index: 213484 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.5568. Min Act: -0.0002

Data Index: 98248 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.4788. Min Act: -0.0002

Data Index: 388225 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.4996. Min Act: -0.0002

Data Index: 419787 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 1.7707. Min Range: -1.7707

Max Act: 1.4922. Min Act: -0.0002

Data Index: 394684 (C4 (Web Text))

Max Activating Token Index: 410