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

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

Neuron 4447 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: 1.2718. Min Range: -1.2718

Max Act: 1.2518. Min Act: -0.0000

Data Index: 1258554 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.1001. Min Act: -0.0000

Data Index: 206371 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.2666. Min Act: -0.0000

Data Index: 781491 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.1511. Min Act: -0.0000

Data Index: 284269 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.1837. Min Act: -0.0000

Data Index: 377976 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.2198. Min Act: -0.0000

Data Index: 1192708 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.2146. Min Act: -0.0000

Data Index: 1080116 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.2718. Min Act: -0.0000

Data Index: 169076 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.1603. Min Act: -0.0000

Data Index: 557745 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.1684. Min Act: -0.0000

Data Index: 99138 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.1299. Min Act: -0.0000

Data Index: 1219067 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.1755. Min Act: -0.0000

Data Index: 849144 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.0647. Min Act: -0.0000

Data Index: 1113386 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.0176. Min Act: -0.0000

Data Index: 1068683 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 1.2718. Min Range: -1.2718

Max Act: 1.0633. Min Act: -0.0000

Data Index: 727209 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.9759. Min Act: -0.0000

Data Index: 430304 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.9658. Min Act: -0.0000

Data Index: 1107741 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8941. Min Act: -0.0000

Data Index: 259189 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8857. Min Act: -0.0000

Data Index: 138254 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 1.2718. Min Range: -1.2718

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1047456 (C4 (Web Text))

Max Activating Token Index: 297