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

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

Neuron 191 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.2002. Min Act: -0.0001

Data Index: 711497 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1972. Min Act: -0.0001

Data Index: 1603145 (Python Code)

Max Activating Token Index: 644

Text #2

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1870. Min Act: -0.0001

Data Index: 197880 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1746. Min Act: -0.0001

Data Index: 3498 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1784. Min Act: -0.0001

Data Index: 103905 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1777. Min Act: -0.0001

Data Index: 1051761 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1740. Min Act: -0.0001

Data Index: 1421246 (Python Code)

Max Activating Token Index: 1019

Text #7

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1737. Min Act: -0.0001

Data Index: 1402277 (Python Code)

Max Activating Token Index: 840

Text #8

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1630. Min Act: -0.0001

Data Index: 1014139 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1728. Min Act: -0.0001

Data Index: 1148702 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1741. Min Act: -0.0001

Data Index: 606683 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1691. Min Act: -0.0001

Data Index: 884534 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1689. Min Act: -0.0001

Data Index: 752208 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1655. Min Act: -0.0001

Data Index: 371084 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1598. Min Act: -0.0001

Data Index: 812769 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1662. Min Act: -0.0001

Data Index: 1428319 (Python Code)

Max Activating Token Index: 1015

Text #16

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1650. Min Act: -0.0001

Data Index: 1645443 (Python Code)

Max Activating Token Index: 129

Text #17

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1650. Min Act: -0.0001

Data Index: 1197054 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1571. Min Act: -0.0001

Data Index: 290436 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1626. Min Act: -0.0001

Data Index: 1192867 (C4 (Web Text))

Max Activating Token Index: 592