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

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

Neuron 1918 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: 0.0465. Min Range: -0.0465

Max Act: 0.0450. Min Act: -0.0005

Data Index: 1257860 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0465. Min Act: -0.0005

Data Index: 156330 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0424. Min Act: -0.0005

Data Index: 57738 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0425. Min Act: -0.0005

Data Index: 345396 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0388. Min Act: -0.0005

Data Index: 515068 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0392. Min Act: -0.0005

Data Index: 1086609 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0412. Min Act: -0.0005

Data Index: 1061374 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0363. Min Act: -0.0005

Data Index: 818330 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0374. Min Act: -0.0005

Data Index: 1152098 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0376. Min Act: -0.0005

Data Index: 976373 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0377. Min Act: -0.0005

Data Index: 607013 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0375. Min Act: -0.0005

Data Index: 825337 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0359. Min Act: -0.0006

Data Index: 29388 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0352. Min Act: -0.0005

Data Index: 10695 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0367. Min Act: -0.0005

Data Index: 424543 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0357. Min Act: -0.0005

Data Index: 1194485 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0354. Min Act: -0.0005

Data Index: 224205 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0346. Min Act: -0.0005

Data Index: 1165863 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0360. Min Act: -0.0005

Data Index: 1314110 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0356. Min Act: -0.0005

Data Index: 106872 (C4 (Web Text))

Max Activating Token Index: 531