Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2027 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0638. Min Act: -0.0006

Data Index: 1230921 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0589. Min Act: -0.0006

Data Index: 49556 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0609. Min Act: -0.0006

Data Index: 671433 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0549. Min Act: -0.0006

Data Index: 863235 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0555. Min Act: -0.0006

Data Index: 663084 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0540. Min Act: -0.0006

Data Index: 1129001 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0517. Min Act: -0.0006

Data Index: 1001934 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0524. Min Act: -0.0006

Data Index: 916025 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0520. Min Act: -0.0006

Data Index: 406700 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0518. Min Act: -0.0006

Data Index: 464390 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0506. Min Act: -0.0006

Data Index: 400527 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0522. Min Act: -0.0006

Data Index: 1156379 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0507. Min Act: -0.0006

Data Index: 108514 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0452. Min Act: -0.0006

Data Index: 180026 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0493. Min Act: -0.0006

Data Index: 251306 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0495. Min Act: -0.0006

Data Index: 195748 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0493. Min Act: -0.0006

Data Index: 1079146 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0502. Min Act: -0.0006

Data Index: 165752 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0510. Min Act: -0.0006

Data Index: 418378 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0498. Min Act: -0.0006

Data Index: 996787 (C4 (Web Text))

Max Activating Token Index: 28