Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1065 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.5445. Min Act: -0.0005

Data Index: 449118 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.4358. Min Act: -0.0006

Data Index: 1121347 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.4566. Min Act: -0.0005

Data Index: 1104041 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.4203. Min Act: -0.0006

Data Index: 280054 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.2992. Min Act: -0.0006

Data Index: 875071 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.3483. Min Act: -0.0006

Data Index: 781248 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.2559. Min Act: -0.0005

Data Index: 618368 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.1876. Min Act: -0.0005

Data Index: 1160080 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.1813. Min Act: -0.0005

Data Index: 768410 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.1384. Min Act: -0.0006

Data Index: 357472 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.1679. Min Act: -0.0006

Data Index: 7586 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.2430. Min Act: -0.0006

Data Index: 136323 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.1950. Min Act: -0.0006

Data Index: 1189532 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.1251. Min Act: -0.0006

Data Index: 19621 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.1557. Min Act: -0.0006

Data Index: 463914 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.1831. Min Act: -0.0006

Data Index: 810499 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.1110. Min Act: -0.0006

Data Index: 1277155 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.1381. Min Act: -0.0006

Data Index: 85139 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.1662. Min Act: -0.0005

Data Index: 1136646 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 1.5445. Min Range: -1.5445

Max Act: 1.0908. Min Act: -0.0005

Data Index: 1215841 (C4 (Web Text))

Max Activating Token Index: 624