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

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

Neuron 725 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: 0.0419. Min Range: -0.0419

Max Act: 0.0419. Min Act: -0.0006

Data Index: 1006266 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0410. Min Act: -0.0006

Data Index: 1245781 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0377. Min Act: -0.0006

Data Index: 621611 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0363. Min Act: -0.0006

Data Index: 911092 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0376. Min Act: -0.0006

Data Index: 565462 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0378. Min Act: -0.0006

Data Index: 336859 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0361. Min Act: -0.0006

Data Index: 718388 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0346. Min Act: -0.0006

Data Index: 53613 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0381. Min Act: -0.0006

Data Index: 810220 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0359. Min Act: -0.0006

Data Index: 530216 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0350. Min Act: -0.0006

Data Index: 316313 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0343. Min Act: -0.0006

Data Index: 1332629 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0346. Min Act: -0.0006

Data Index: 109200 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0339. Min Act: -0.0006

Data Index: 1192423 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0349. Min Act: -0.0006

Data Index: 388945 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0328. Min Act: -0.0006

Data Index: 800544 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0326. Min Act: -0.0006

Data Index: 1157755 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0352. Min Act: -0.0006

Data Index: 351306 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0338. Min Act: -0.0006

Data Index: 285069 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0338. Min Act: -0.0006

Data Index: 269450 (C4 (Web Text))

Max Activating Token Index: 114