Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3910 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.4256. Min Act: -0.0000

Data Index: 160832 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3886. Min Act: -0.0000

Data Index: 375195 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3718. Min Act: -0.0000

Data Index: 1291574 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3756. Min Act: -0.0000

Data Index: 1172029 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3182. Min Act: -0.0000

Data Index: 1048022 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1068796 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2746. Min Act: -0.0000

Data Index: 416220 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2671. Min Act: -0.0000

Data Index: 1109201 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1642229 (Python Code)

Max Activating Token Index: 791

Text #9

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2271. Min Act: -0.0000

Data Index: 419569 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2342. Min Act: -0.0000

Data Index: 273723 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2086. Min Act: -0.0000

Data Index: 1054219 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2283. Min Act: -0.0000

Data Index: 907574 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2145. Min Act: -0.0000

Data Index: 51755 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2187. Min Act: -0.0000

Data Index: 727169 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2034. Min Act: -0.0000

Data Index: 891717 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1028499 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.1912. Min Act: -0.0000

Data Index: 1331532 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1410893 (Python Code)

Max Activating Token Index: 127

Text #19

Max Range: 0.4256. Min Range: -0.4256

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1338176 (C4 (Web Text))

Max Activating Token Index: 109