Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 668 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.2156. Min Act: -0.0001

Data Index: 990303 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1878. Min Act: -0.0000

Data Index: 83225 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1890. Min Act: -0.0000

Data Index: 599727 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1858. Min Act: -0.0000

Data Index: 450595 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1848. Min Act: -0.0000

Data Index: 952956 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1784. Min Act: -0.0001

Data Index: 733769 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1828. Min Act: -0.0000

Data Index: 1098899 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1756. Min Act: -0.0001

Data Index: 880900 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1662. Min Act: -0.0001

Data Index: 769715 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1635. Min Act: -0.0000

Data Index: 621362 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1567. Min Act: -0.0000

Data Index: 1097165 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1613. Min Act: -0.0001

Data Index: 979274 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1599. Min Act: -0.0000

Data Index: 855362 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1608. Min Act: -0.0001

Data Index: 610737 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1575. Min Act: -0.0001

Data Index: 734021 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1589. Min Act: -0.0000

Data Index: 790731 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1562. Min Act: -0.0000

Data Index: 1034090 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1516. Min Act: -0.0000

Data Index: 1307883 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1499. Min Act: -0.0001

Data Index: 434691 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.2156. Min Range: -0.2156

Max Act: 0.1386. Min Act: -0.0001

Data Index: 354856 (C4 (Web Text))

Max Activating Token Index: 816