Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3144 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0293. Min Act: -0.0003

Data Index: 125252 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0364. Min Act: -0.0003

Data Index: 822797 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0374. Min Act: -0.0004

Data Index: 1237237 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0361. Min Act: -0.0003

Data Index: 1101653 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0282. Min Act: -0.0003

Data Index: 299198 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0325. Min Act: -0.0003

Data Index: 556820 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0345. Min Act: -0.0003

Data Index: 144681 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0336. Min Act: -0.0004

Data Index: 140131 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0332. Min Act: -0.0003

Data Index: 152385 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0269. Min Act: -0.0003

Data Index: 189608 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0342. Min Act: -0.0003

Data Index: 651384 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0290. Min Act: -0.0003

Data Index: 660865 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0352. Min Act: -0.0003

Data Index: 741786 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1038463 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0329. Min Act: -0.0003

Data Index: 937685 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0239. Min Act: -0.0003

Data Index: 28372 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0322. Min Act: -0.0003

Data Index: 1170360 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0317. Min Act: -0.0003

Data Index: 702110 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0274. Min Act: -0.0003

Data Index: 333295 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0301. Min Act: -0.0004

Data Index: 79568 (C4 (Web Text))

Max Activating Token Index: 921