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

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

Neuron 1768 in Layer 2

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: -0.0005

Data Index: 1198569 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0539. Min Act: -0.0005

Data Index: 374924 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0559. Min Act: -0.0005

Data Index: 1191016 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0500. Min Act: -0.0005

Data Index: 51083 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0482. Min Act: -0.0005

Data Index: 780775 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0478. Min Act: -0.0005

Data Index: 554674 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0484. Min Act: -0.0005

Data Index: 708966 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0464. Min Act: -0.0005

Data Index: 1319264 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0427. Min Act: -0.0005

Data Index: 1123770 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0482. Min Act: -0.0005

Data Index: 361026 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0446. Min Act: -0.0005

Data Index: 1025189 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0474. Min Act: -0.0005

Data Index: 577055 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0479. Min Act: -0.0005

Data Index: 688325 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0436. Min Act: -0.0005

Data Index: 45142 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0445. Min Act: -0.0005

Data Index: 555721 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0453. Min Act: -0.0005

Data Index: 241514 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0452. Min Act: -0.0005

Data Index: 463304 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0469. Min Act: -0.0005

Data Index: 1147969 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0445. Min Act: -0.0005

Data Index: 157827 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0455. Min Act: -0.0005

Data Index: 1069884 (C4 (Web Text))

Max Activating Token Index: 423