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

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

Neuron 639 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1278360 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1145997 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0651. Min Act: -0.0002

Data Index: 284370 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0647. Min Act: -0.0002

Data Index: 925587 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0646. Min Act: -0.0002

Data Index: 475131 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1171008 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0642. Min Act: -0.0002

Data Index: 78250 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0639. Min Act: -0.0002

Data Index: 302754 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0630. Min Act: -0.0002

Data Index: 742441 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0629. Min Act: -0.0002

Data Index: 558285 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0629. Min Act: -0.0002

Data Index: 963988 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0627. Min Act: -0.0002

Data Index: 141922 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0625. Min Act: -0.0002

Data Index: 995997 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1178391 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0618. Min Act: -0.0002

Data Index: 240224 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0617. Min Act: -0.0002

Data Index: 977691 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1289149 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1178579 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0615. Min Act: -0.0002

Data Index: 221639 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0615. Min Act: -0.0002

Data Index: 578831 (C4 (Web Text))

Max Activating Token Index: 3