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

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

Neuron 3635 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: 1.6811. Min Range: -1.6811

Max Act: 1.6811. Min Act: -0.0000

Data Index: 811231 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.6675. Min Act: -0.0000

Data Index: 1612064 (Python Code)

Max Activating Token Index: 699

Text #2

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4801. Min Act: -0.0000

Data Index: 1421471 (Python Code)

Max Activating Token Index: 55

Text #3

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4690. Min Act: -0.0000

Data Index: 1478997 (Python Code)

Max Activating Token Index: 763

Text #4

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4752. Min Act: -0.0000

Data Index: 1377523 (Python Code)

Max Activating Token Index: 907

Text #5

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.3956. Min Act: -0.0000

Data Index: 1494724 (Python Code)

Max Activating Token Index: 569

Text #6

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.3533. Min Act: -0.0000

Data Index: 1651339 (Python Code)

Max Activating Token Index: 766

Text #7

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.2954. Min Act: -0.0000

Data Index: 168612 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.3195. Min Act: -0.0000

Data Index: 1521082 (Python Code)

Max Activating Token Index: 984

Text #9

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.2684. Min Act: -0.0000

Data Index: 1407620 (Python Code)

Max Activating Token Index: 272

Text #10

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.2268. Min Act: -0.0000

Data Index: 433126 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.2468. Min Act: -0.0000

Data Index: 780424 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.2416. Min Act: -0.0000

Data Index: 277378 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.2166. Min Act: -0.0000

Data Index: 1126691 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.1114. Min Act: -0.0000

Data Index: 1459740 (Python Code)

Max Activating Token Index: 518

Text #15

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1413006 (Python Code)

Max Activating Token Index: 527

Text #16

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.0360. Min Act: -0.0000

Data Index: 741853 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.0333. Min Act: -0.0000

Data Index: 1579577 (Python Code)

Max Activating Token Index: 647

Text #18

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.0797. Min Act: -0.0000

Data Index: 918750 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.0252. Min Act: -0.0000

Data Index: 440120 (C4 (Web Text))

Max Activating Token Index: 744