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

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

Neuron 2082 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.7193. Min Act: -0.0000

Data Index: 784498 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.7216. Min Act: -0.0000

Data Index: 49242 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1629750 (Python Code)

Max Activating Token Index: 694

Text #3

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5672. Min Act: -0.0000

Data Index: 780264 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1603472 (Python Code)

Max Activating Token Index: 793

Text #5

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5843. Min Act: -0.0000

Data Index: 519932 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1202449 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5205. Min Act: -0.0000

Data Index: 831977 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5291. Min Act: -0.0000

Data Index: 405690 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5460. Min Act: -0.0000

Data Index: 346631 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5406. Min Act: -0.0000

Data Index: 230395 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1395963 (Python Code)

Max Activating Token Index: 5

Text #12

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1367588 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5540. Min Act: -0.0000

Data Index: 435278 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1389087 (Python Code)

Max Activating Token Index: 18

Text #15

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5084. Min Act: -0.0000

Data Index: 48239 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5005. Min Act: -0.0000

Data Index: 1302395 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1455588 (Python Code)

Max Activating Token Index: 635

Text #18

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5326. Min Act: -0.0000

Data Index: 898393 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.7216. Min Range: -0.7216

Max Act: 0.5094. Min Act: -0.0000

Data Index: 424734 (C4 (Web Text))

Max Activating Token Index: 936