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

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

Neuron 526 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: 0.0781. Min Range: -0.0781

Max Act: 0.0781. Min Act: -0.0002

Data Index: 512278 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0684. Min Act: -0.0002

Data Index: 978531 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0473. Min Act: -0.0001

Data Index: 1411425 (Python Code)

Max Activating Token Index: 364

Text #3

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0410. Min Act: -0.0001

Data Index: 407341 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0420. Min Act: -0.0002

Data Index: 446366 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0367. Min Act: -0.0002

Data Index: 413199 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0358. Min Act: -0.0001

Data Index: 1432098 (Python Code)

Max Activating Token Index: 101

Text #7

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0336. Min Act: 0.0001

Data Index: 1217926 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1037088 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1040925 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0289. Min Act: 0.0000

Data Index: 261695 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0275. Min Act: -0.0001

Data Index: 1493293 (Python Code)

Max Activating Token Index: 876

Text #12

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1450735 (Python Code)

Max Activating Token Index: 292

Text #13

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0280. Min Act: 0.0000

Data Index: 187244 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1634330 (Python Code)

Max Activating Token Index: 911

Text #15

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0248. Min Act: -0.0001

Data Index: 1481534 (Python Code)

Max Activating Token Index: 185

Text #16

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0252. Min Act: -0.0000

Data Index: 393335 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1255352 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0248. Min Act: -0.0002

Data Index: 971809 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0249. Min Act: -0.0001

Data Index: 890066 (C4 (Web Text))

Max Activating Token Index: 1023