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

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

Neuron 1193 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0907. Min Act: -0.0002

Data Index: 1113220 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0764. Min Act: -0.0002

Data Index: 54351 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1178890 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1197841 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0686. Min Act: -0.0002

Data Index: 240863 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1138154 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0690. Min Act: -0.0002

Data Index: 619024 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1105592 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0599. Min Act: -0.0002

Data Index: 822811 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1291052 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0611. Min Act: -0.0002

Data Index: 78758 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0546. Min Act: -0.0002

Data Index: 955219 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0620. Min Act: -0.0002

Data Index: 827001 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0632. Min Act: -0.0002

Data Index: 883632 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1086008 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1047422 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1121024 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1113724 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0563. Min Act: -0.0002

Data Index: 543106 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0619. Min Act: -0.0002

Data Index: 307772 (C4 (Web Text))

Max Activating Token Index: 716