Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2576 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.7059. Min Act: -0.0000

Data Index: 765153 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6692. Min Act: -0.0000

Data Index: 18713 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1042438 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1102443 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6686. Min Act: -0.0000

Data Index: 555792 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1054415 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6872. Min Act: -0.0000

Data Index: 159998 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6390. Min Act: -0.0000

Data Index: 352708 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6683. Min Act: -0.0000

Data Index: 697989 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6415. Min Act: -0.0000

Data Index: 1020063 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6067. Min Act: -0.0000

Data Index: 439460 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6321. Min Act: -0.0000

Data Index: 712576 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1177442 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6067. Min Act: -0.0000

Data Index: 117834 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6659. Min Act: -0.0000

Data Index: 730228 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6589. Min Act: -0.0000

Data Index: 354296 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.5996. Min Act: -0.0000

Data Index: 255744 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6457. Min Act: -0.0000

Data Index: 997104 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6302. Min Act: -0.0000

Data Index: 877450 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.7059. Min Range: -0.7059

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1213495 (C4 (Web Text))

Max Activating Token Index: 133