Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3008 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1911. Min Act: -0.0001

Data Index: 149939 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1125463 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1996. Min Act: -0.0001

Data Index: 1182541 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1700. Min Act: -0.0001

Data Index: 698734 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1730. Min Act: -0.0001

Data Index: 1153247 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1650. Min Act: -0.0001

Data Index: 70834 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1736. Min Act: -0.0001

Data Index: 282988 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1632. Min Act: -0.0001

Data Index: 7529 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1664. Min Act: -0.0001

Data Index: 1218062 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1780. Min Act: -0.0001

Data Index: 442552 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1713. Min Act: -0.0001

Data Index: 877006 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1224255 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1781. Min Act: -0.0001

Data Index: 398757 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1590. Min Act: -0.0001

Data Index: 1006951 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1636. Min Act: -0.0001

Data Index: 1258886 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1676. Min Act: -0.0001

Data Index: 375437 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1674. Min Act: -0.0001

Data Index: 399545 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1567. Min Act: -0.0001

Data Index: 582239 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1515. Min Act: -0.0001

Data Index: 932773 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.1996. Min Range: -0.1996

Max Act: 0.1586. Min Act: -0.0001

Data Index: 347003 (C4 (Web Text))

Max Activating Token Index: 694