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

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

Neuron 3617 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0536. Min Range: -1.0536

Max Act: 1.0536. Min Act: -0.0002

Data Index: 417436 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9797. Min Act: -0.0003

Data Index: 146465 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 1.0536. Min Range: -1.0536

Max Act: 1.0009. Min Act: -0.0002

Data Index: 636977 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9395. Min Act: -0.0003

Data Index: 265234 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9330. Min Act: -0.0003

Data Index: 496831 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9291. Min Act: -0.0003

Data Index: 1163681 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9226. Min Act: -0.0003

Data Index: 1058443 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9535. Min Act: -0.0003

Data Index: 137334 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9447. Min Act: -0.0003

Data Index: 381422 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9106. Min Act: -0.0003

Data Index: 723378 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9056. Min Act: -0.0002

Data Index: 1078559 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.9413. Min Act: -0.0003

Data Index: 365639 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8789. Min Act: -0.0003

Data Index: 1234005 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8717. Min Act: -0.0003

Data Index: 106866 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8401. Min Act: -0.0003

Data Index: 1304390 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8364. Min Act: -0.0003

Data Index: 120244 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8930. Min Act: -0.0003

Data Index: 87274 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8869. Min Act: -0.0002

Data Index: 1035626 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8473. Min Act: -0.0003

Data Index: 529767 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 1.0536. Min Range: -1.0536

Max Act: 0.8187. Min Act: -0.0002

Data Index: 1337222 (C4 (Web Text))

Max Activating Token Index: 93