Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 540 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0417. Min Act: -0.0003

Data Index: 372078 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0434. Min Act: -0.0003

Data Index: 697448 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0424. Min Act: -0.0003

Data Index: 236045 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0419. Min Act: -0.0003

Data Index: 672738 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0413. Min Act: -0.0003

Data Index: 146766 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1282602 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0400. Min Act: -0.0003

Data Index: 886988 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0406. Min Act: -0.0004

Data Index: 950108 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0392. Min Act: -0.0003

Data Index: 256720 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0401. Min Act: -0.0003

Data Index: 691551 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0400. Min Act: -0.0003

Data Index: 508838 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0371. Min Act: -0.0003

Data Index: 573912 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0399. Min Act: -0.0003

Data Index: 349632 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0397. Min Act: -0.0003

Data Index: 734143 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1035460 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0372. Min Act: -0.0003

Data Index: 435599 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0375. Min Act: -0.0003

Data Index: 1300792 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0371. Min Act: -0.0003

Data Index: 927143 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0397. Min Act: -0.0004

Data Index: 778316 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0368. Min Act: -0.0004

Data Index: 670583 (C4 (Web Text))

Max Activating Token Index: 476