Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5437 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3546. Min Range: -1.3546

Max Act: 1.3546. Min Act: -0.0000

Data Index: 44457 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 1.3546. Min Range: -1.3546

Max Act: 1.0860. Min Act: -0.0000

Data Index: 43277 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 1.3546. Min Range: -1.3546

Max Act: 1.0068. Min Act: -0.0000

Data Index: 862899 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 1.3546. Min Range: -1.3546

Max Act: 1.0051. Min Act: -0.0000

Data Index: 1117786 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.9856. Min Act: -0.0000

Data Index: 730425 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.9196. Min Act: -0.0000

Data Index: 86132 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.8868. Min Act: -0.0000

Data Index: 85890 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.9685. Min Act: -0.0000

Data Index: 4715 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.8656. Min Act: -0.0000

Data Index: 435682 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.8597. Min Act: -0.0000

Data Index: 686465 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.7889. Min Act: -0.0000

Data Index: 186979 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.9152. Min Act: -0.0000

Data Index: 809429 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.8760. Min Act: -0.0000

Data Index: 537743 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.8839. Min Act: -0.0000

Data Index: 994659 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.8556. Min Act: -0.0000

Data Index: 737111 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.8242. Min Act: -0.0000

Data Index: 1200756 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.8222. Min Act: -0.0000

Data Index: 675276 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.8647. Min Act: -0.0000

Data Index: 465757 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.8256. Min Act: -0.0000

Data Index: 889421 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 1.3546. Min Range: -1.3546

Max Act: 0.7620. Min Act: -0.0000

Data Index: 71536 (C4 (Web Text))

Max Activating Token Index: 871