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

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

Neuron 670 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0375. Min Range: -3.0375

Max Act: 3.0375. Min Act: -0.0000

Data Index: 112834 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 3.0375. Min Range: -3.0375

Max Act: 2.3331. Min Act: -0.0000

Data Index: 1314016 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 3.0375. Min Range: -3.0375

Max Act: 2.4741. Min Act: -0.0000

Data Index: 157676 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 3.0375. Min Range: -3.0375

Max Act: 1.9682. Min Act: -0.0000

Data Index: 892964 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 3.0375. Min Range: -3.0375

Max Act: 2.0441. Min Act: 0.0000

Data Index: 561172 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 3.0375. Min Range: -3.0375

Max Act: 1.7780. Min Act: -0.0000

Data Index: 1262303 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 3.0375. Min Range: -3.0375

Max Act: 1.9935. Min Act: -0.0000

Data Index: 934608 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 3.0375. Min Range: -3.0375

Max Act: 1.9186. Min Act: -0.0000

Data Index: 650997 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 3.0375. Min Range: -3.0375

Max Act: 1.8059. Min Act: -0.0000

Data Index: 592927 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 3.0375. Min Range: -3.0375

Max Act: 1.8875. Min Act: -0.0000

Data Index: 283583 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 3.0375. Min Range: -3.0375

Max Act: 1.8875. Min Act: 0.0000

Data Index: 174624 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 3.0375. Min Range: -3.0375

Max Act: 1.9937. Min Act: 0.0000

Data Index: 1557969 (Python Code)

Max Activating Token Index: 922

Text #12

Max Range: 3.0375. Min Range: -3.0375

Max Act: 1.9379. Min Act: -0.0000

Data Index: 1269815 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 3.0375. Min Range: -3.0375

Max Act: 1.9083. Min Act: 0.0000

Data Index: 554167 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 3.0375. Min Range: -3.0375

Max Act: 1.7711. Min Act: -0.0000

Data Index: 46559 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 3.0375. Min Range: -3.0375

Max Act: 1.8730. Min Act: 0.0001

Data Index: 1077732 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 3.0375. Min Range: -3.0375

Max Act: 1.6533. Min Act: -0.0000

Data Index: 568264 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 3.0375. Min Range: -3.0375

Max Act: 1.6936. Min Act: -0.0000

Data Index: 1396605 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 3.0375. Min Range: -3.0375

Max Act: 1.7943. Min Act: -0.0000

Data Index: 100318 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 3.0375. Min Range: -3.0375

Max Act: 1.7796. Min Act: -0.0000

Data Index: 145927 (C4 (Web Text))

Max Activating Token Index: 1007