Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2922 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1741. Min Act: -0.0000

Data Index: 158546 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1714. Min Act: -0.0000

Data Index: 397832 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1758. Min Act: -0.0000

Data Index: 721983 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1747. Min Act: -0.0000

Data Index: 255201 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1259286 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1556. Min Act: -0.0000

Data Index: 979095 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1597. Min Act: -0.0000

Data Index: 1070767 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1564. Min Act: -0.0000

Data Index: 664907 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1588. Min Act: -0.0000

Data Index: 609600 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1585. Min Act: -0.0000

Data Index: 677124 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1596. Min Act: -0.0000

Data Index: 83273 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1489. Min Act: -0.0000

Data Index: 329112 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1536. Min Act: -0.0000

Data Index: 358148 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1492. Min Act: -0.0000

Data Index: 541148 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1454. Min Act: -0.0000

Data Index: 856649 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1541. Min Act: -0.0000

Data Index: 829112 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1489. Min Act: -0.0000

Data Index: 104494 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1498. Min Act: -0.0000

Data Index: 790864 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1299124 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1455. Min Act: -0.0000

Data Index: 62212 (C4 (Web Text))

Max Activating Token Index: 672