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

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

Neuron 6080 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0878. Min Act: -0.0002

Data Index: 608597 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0647. Min Act: -0.0002

Data Index: 113438 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0561. Min Act: -0.0002

Data Index: 568151 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0561. Min Act: -0.0002

Data Index: 939580 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0553. Min Act: -0.0002

Data Index: 707745 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0567. Min Act: -0.0002

Data Index: 987717 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0545. Min Act: -0.0002

Data Index: 741154 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0540. Min Act: -0.0002

Data Index: 935271 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1006967 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0512. Min Act: -0.0002

Data Index: 802378 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0551. Min Act: -0.0002

Data Index: 740855 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0569. Min Act: -0.0002

Data Index: 671131 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0522. Min Act: -0.0002

Data Index: 990213 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0497. Min Act: -0.0002

Data Index: 891531 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0503. Min Act: -0.0002

Data Index: 959323 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0535. Min Act: -0.0002

Data Index: 82626 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0514. Min Act: -0.0002

Data Index: 58272 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0511. Min Act: -0.0002

Data Index: 157742 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1321073 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0512. Min Act: -0.0002

Data Index: 723874 (C4 (Web Text))

Max Activating Token Index: 106