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

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

Neuron 291 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.5881. Min Act: -0.0000

Data Index: 948133 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.5350. Min Act: -0.0000

Data Index: 1317726 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.5390. Min Act: -0.0000

Data Index: 499190 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.4219. Min Act: -0.0000

Data Index: 274634 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.2014. Min Act: -0.0000

Data Index: 991011 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.2006. Min Act: -0.0000

Data Index: 112716 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.2736. Min Act: -0.0000

Data Index: 965318 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.3812. Min Act: -0.0000

Data Index: 1065533 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.4007. Min Act: -0.0000

Data Index: 649501 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.0469. Min Act: -0.0000

Data Index: 1211560 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.1670. Min Act: -0.0000

Data Index: 1300548 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.4013. Min Act: -0.0000

Data Index: 675783 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.9175. Min Act: -0.0000

Data Index: 1334717 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.2241. Min Act: -0.0000

Data Index: 936992 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.1852. Min Act: -0.0000

Data Index: 453487 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.1842. Min Act: -0.0000

Data Index: 107232 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.1615. Min Act: -0.0000

Data Index: 1316836 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.1426. Min Act: -0.0000

Data Index: 608764 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 4.5881. Min Range: -4.5881

Max Act: 4.3083. Min Act: -0.0000

Data Index: 282293 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 4.5881. Min Range: -4.5881

Max Act: 3.9762. Min Act: -0.0000

Data Index: 590086 (C4 (Web Text))

Max Activating Token Index: 56