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

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

Neuron 3596 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: 0.0602. Min Range: -0.0602

Max Act: 0.0602. Min Act: -0.0002

Data Index: 538956 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1039003 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0572. Min Act: -0.0002

Data Index: 439032 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0561. Min Act: -0.0002

Data Index: 522191 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0553. Min Act: -0.0002

Data Index: 131482 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1322218 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0553. Min Act: -0.0002

Data Index: 176209 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0547. Min Act: -0.0002

Data Index: 827674 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0536. Min Act: -0.0002

Data Index: 861470 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0536. Min Act: -0.0002

Data Index: 10437 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0539. Min Act: -0.0002

Data Index: 62005 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0536. Min Act: -0.0002

Data Index: 12024 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1037247 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0532. Min Act: -0.0002

Data Index: 479060 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0539. Min Act: -0.0002

Data Index: 778026 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0533. Min Act: -0.0002

Data Index: 559866 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0523. Min Act: -0.0002

Data Index: 55476 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1171814 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1165975 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1332890 (C4 (Web Text))

Max Activating Token Index: 529