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

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

Neuron 1572 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0333. Min Act: -0.0005

Data Index: 1393572 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0299. Min Act: -0.0006

Data Index: 940051 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0291. Min Act: -0.0006

Data Index: 149342 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0270. Min Act: -0.0006

Data Index: 553588 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0280. Min Act: -0.0006

Data Index: 49516 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0275. Min Act: -0.0006

Data Index: 431715 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0269. Min Act: -0.0006

Data Index: 758486 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0275. Min Act: -0.0006

Data Index: 153313 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0267. Min Act: -0.0006

Data Index: 94377 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1313360 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0272. Min Act: -0.0006

Data Index: 752261 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0271. Min Act: -0.0006

Data Index: 540694 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0271. Min Act: -0.0006

Data Index: 879574 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0270. Min Act: -0.0006

Data Index: 635127 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0276. Min Act: -0.0006

Data Index: 1169690 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0270. Min Act: -0.0006

Data Index: 593498 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0241. Min Act: -0.0006

Data Index: 440330 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0269. Min Act: -0.0006

Data Index: 427018 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0273. Min Act: -0.0006

Data Index: 990977 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0256. Min Act: -0.0006

Data Index: 15381 (C4 (Web Text))

Max Activating Token Index: 619