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

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

Neuron 4708 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.5850. Min Act: -0.0000

Data Index: 444364 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.4367. Min Act: -0.0001

Data Index: 1329066 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3500. Min Act: -0.0001

Data Index: 1012110 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.2460. Min Act: -0.0000

Data Index: 733344 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.2878. Min Act: -0.0000

Data Index: 1303566 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3267. Min Act: -0.0001

Data Index: 55640 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.1744. Min Act: -0.0000

Data Index: 779535 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.2311. Min Act: -0.0001

Data Index: 760081 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.1843. Min Act: -0.0000

Data Index: 1015593 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.1777. Min Act: -0.0001

Data Index: 850611 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.2861. Min Act: -0.0000

Data Index: 599354 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.1672. Min Act: -0.0000

Data Index: 341610 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.1310. Min Act: -0.0000

Data Index: 551542 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.1534. Min Act: -0.0001

Data Index: 1165155 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.1784. Min Act: -0.0001

Data Index: 1032616 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.2433. Min Act: -0.0001

Data Index: 735043 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.1889. Min Act: -0.0000

Data Index: 444916 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.1528. Min Act: -0.0001

Data Index: 1178696 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.1332. Min Act: -0.0001

Data Index: 1211619 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.0586. Min Act: -0.0001

Data Index: 470040 (C4 (Web Text))

Max Activating Token Index: 371