Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1203 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.7628. Min Act: -0.0005

Data Index: 993644 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.7216. Min Act: -0.0005

Data Index: 262631 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6917. Min Act: -0.0005

Data Index: 1031582 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6674. Min Act: -0.0005

Data Index: 374313 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6420. Min Act: -0.0005

Data Index: 323036 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6752. Min Act: -0.0005

Data Index: 881230 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6231. Min Act: -0.0005

Data Index: 135799 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6621. Min Act: -0.0005

Data Index: 729753 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6009. Min Act: -0.0005

Data Index: 937181 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6578. Min Act: -0.0005

Data Index: 1159806 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6314. Min Act: -0.0005

Data Index: 582697 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6286. Min Act: -0.0005

Data Index: 589731 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6477. Min Act: -0.0005

Data Index: 307176 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6685. Min Act: -0.0005

Data Index: 589721 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6175. Min Act: -0.0005

Data Index: 81812 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6319. Min Act: -0.0005

Data Index: 1049060 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.5814. Min Act: -0.0005

Data Index: 119736 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6022. Min Act: -0.0005

Data Index: 1339428 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6993. Min Act: -0.0005

Data Index: 657057 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.5928. Min Act: -0.0005

Data Index: 880393 (C4 (Web Text))

Max Activating Token Index: 199