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

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

Neuron 503 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3860. Min Act: -0.0000

Data Index: 461778 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1192812 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3329. Min Act: -0.0000

Data Index: 345652 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3076. Min Act: -0.0000

Data Index: 404679 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2929. Min Act: -0.0000

Data Index: 922640 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1065687 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3210. Min Act: -0.0000

Data Index: 77387 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2803. Min Act: -0.0000

Data Index: 997136 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2685. Min Act: -0.0000

Data Index: 766217 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2777. Min Act: -0.0000

Data Index: 212237 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2616. Min Act: -0.0000

Data Index: 154136 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2783. Min Act: -0.0000

Data Index: 491302 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2834. Min Act: -0.0000

Data Index: 485608 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2683. Min Act: -0.0000

Data Index: 612891 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2519. Min Act: -0.0000

Data Index: 697759 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2743. Min Act: -0.0000

Data Index: 379273 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2456. Min Act: -0.0000

Data Index: 849106 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2624. Min Act: -0.0000

Data Index: 364079 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1267288 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2605. Min Act: -0.0000

Data Index: 364590 (C4 (Web Text))

Max Activating Token Index: 113