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

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

Neuron 5872 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: 0.0539. Min Range: -0.0539

Max Act: 0.0536. Min Act: -0.0002

Data Index: 145793 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1111005 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0518. Min Act: -0.0002

Data Index: 210986 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1052431 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0519. Min Act: -0.0002

Data Index: 213674 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1007143 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0488. Min Act: -0.0002

Data Index: 122192 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0487. Min Act: -0.0002

Data Index: 439861 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0490. Min Act: -0.0002

Data Index: 233773 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0485. Min Act: -0.0002

Data Index: 150230 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0491. Min Act: -0.0002

Data Index: 1203081 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1171122 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0477. Min Act: -0.0002

Data Index: 632370 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0488. Min Act: -0.0002

Data Index: 726987 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0482. Min Act: -0.0002

Data Index: 603970 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0475. Min Act: -0.0002

Data Index: 252684 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0479. Min Act: -0.0002

Data Index: 879855 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0474. Min Act: -0.0002

Data Index: 140460 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0466. Min Act: -0.0002

Data Index: 858903 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.0539. Min Range: -0.0539

Max Act: 0.0460. Min Act: -0.0002

Data Index: 909647 (C4 (Web Text))

Max Activating Token Index: 364