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

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

Neuron 5153 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.7865. Min Act: -0.0000

Data Index: 138410 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.5662. Min Act: -0.0000

Data Index: 978768 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.6308. Min Act: -0.0000

Data Index: 235672 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.5968. Min Act: -0.0000

Data Index: 103828 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.4678. Min Act: -0.0000

Data Index: 247000 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.5386. Min Act: -0.0000

Data Index: 1082842 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.4026. Min Act: -0.0000

Data Index: 913176 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.3810. Min Act: -0.0000

Data Index: 813905 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.4381. Min Act: -0.0000

Data Index: 1283353 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.3292. Min Act: -0.0000

Data Index: 954858 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1292585 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.3285. Min Act: -0.0000

Data Index: 568723 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.3180. Min Act: -0.0000

Data Index: 888539 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.2503. Min Act: -0.0000

Data Index: 57275 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.3896. Min Act: -0.0000

Data Index: 1038499 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.3144. Min Act: -0.0000

Data Index: 494373 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.3578. Min Act: -0.0000

Data Index: 465560 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.2778. Min Act: -0.0000

Data Index: 1331937 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.3304. Min Act: -0.0000

Data Index: 191644 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 1.7865. Min Range: -1.7865

Max Act: 1.2583. Min Act: -0.0000

Data Index: 233920 (C4 (Web Text))

Max Activating Token Index: 332