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

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

Neuron 1392 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1109485 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0420. Min Act: -0.0002

Data Index: 221838 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0382. Min Act: -0.0002

Data Index: 744132 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0376. Min Act: -0.0002

Data Index: 541770 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1295348 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0367. Min Act: -0.0002

Data Index: 351274 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1358533 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1212299 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1012786 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0352. Min Act: -0.0002

Data Index: 676061 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0336. Min Act: -0.0002

Data Index: 597632 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0357. Min Act: -0.0002

Data Index: 365151 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0341. Min Act: -0.0002

Data Index: 167774 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1278540 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0347. Min Act: -0.0002

Data Index: 598377 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0342. Min Act: -0.0002

Data Index: 274970 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1075498 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0319. Min Act: -0.0002

Data Index: 310062 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0319. Min Act: -0.0002

Data Index: 888856 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0312. Min Act: -0.0002

Data Index: 16878 (C4 (Web Text))

Max Activating Token Index: 342