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

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

Neuron 4127 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.9989. Min Act: -0.0001

Data Index: 875014 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.7657. Min Act: -0.0001

Data Index: 286187 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.6614. Min Act: -0.0001

Data Index: 1215256 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.7274. Min Act: -0.0001

Data Index: 1341993 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.6907. Min Act: -0.0001

Data Index: 1281212 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.6162. Min Act: -0.0001

Data Index: 554624 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.6580. Min Act: -0.0001

Data Index: 404882 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.6649. Min Act: -0.0001

Data Index: 915637 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.5990. Min Act: -0.0001

Data Index: 525100 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.6013. Min Act: -0.0001

Data Index: 795477 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.5566. Min Act: -0.0001

Data Index: 440718 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.6038. Min Act: -0.0001

Data Index: 827780 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.5421. Min Act: -0.0001

Data Index: 339531 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.5595. Min Act: -0.0001

Data Index: 245560 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.5205. Min Act: -0.0001

Data Index: 1349014 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.5493. Min Act: -0.0001

Data Index: 367050 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.5215. Min Act: -0.0001

Data Index: 1089177 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.5430. Min Act: -0.0001

Data Index: 2052 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.5232. Min Act: -0.0001

Data Index: 944193 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 0.9989. Min Range: -0.9989

Max Act: 0.4730. Min Act: -0.0001

Data Index: 687010 (C4 (Web Text))

Max Activating Token Index: 925