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

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

Neuron 3248 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: 0.9525. Min Range: -0.9525

Max Act: 0.9331. Min Act: -0.0000

Data Index: 1008824 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.9525. Min Act: -0.0000

Data Index: 1255697 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1133060 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8917. Min Act: -0.0000

Data Index: 248845 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8660. Min Act: -0.0000

Data Index: 1148783 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1310478 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8784. Min Act: -0.0000

Data Index: 1222126 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8442. Min Act: -0.0000

Data Index: 513290 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7845. Min Act: -0.0000

Data Index: 1341871 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8560. Min Act: -0.0000

Data Index: 361773 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1083732 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8122. Min Act: -0.0000

Data Index: 86968 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8118. Min Act: -0.0000

Data Index: 944928 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7828. Min Act: -0.0000

Data Index: 816141 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7847. Min Act: -0.0000

Data Index: 460072 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7247. Min Act: -0.0000

Data Index: 91762 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1104040 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6786. Min Act: -0.0000

Data Index: 1229910 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7002. Min Act: -0.0000

Data Index: 378074 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1320839 (C4 (Web Text))

Max Activating Token Index: 97