Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2519 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0496. Min Act: -0.0002

Data Index: 243722 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1197517 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0474. Min Act: -0.0002

Data Index: 78464 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0462. Min Act: -0.0002

Data Index: 715811 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0412. Min Act: -0.0003

Data Index: 799919 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0406. Min Act: -0.0002

Data Index: 211026 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0401. Min Act: -0.0002

Data Index: 624192 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1190807 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1196696 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1100594 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0378. Min Act: -0.0002

Data Index: 494029 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0372. Min Act: -0.0002

Data Index: 366863 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0361. Min Act: -0.0002

Data Index: 221543 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0368. Min Act: -0.0002

Data Index: 107002 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0354. Min Act: -0.0002

Data Index: 406249 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0352. Min Act: -0.0003

Data Index: 252012 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0356. Min Act: -0.0003

Data Index: 50203 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0348. Min Act: -0.0002

Data Index: 674619 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0350. Min Act: -0.0002

Data Index: 721753 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.0496. Min Range: -0.0496

Max Act: 0.0349. Min Act: -0.0002

Data Index: 985360 (C4 (Web Text))

Max Activating Token Index: 771