Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 565 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0292. Min Act: -0.0006

Data Index: 1485779 (Python Code)

Max Activating Token Index: 199

Text #1

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0265. Min Act: -0.0006

Data Index: 1421798 (Python Code)

Max Activating Token Index: 945

Text #2

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1640250 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0237. Min Act: -0.0006

Data Index: 1384275 (Python Code)

Max Activating Token Index: 691

Text #4

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0230. Min Act: -0.0006

Data Index: 1438078 (Python Code)

Max Activating Token Index: 440

Text #5

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1546670 (Python Code)

Max Activating Token Index: 593

Text #6

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1583340 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0232. Min Act: -0.0005

Data Index: 1570798 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1636590 (Python Code)

Max Activating Token Index: 474

Text #9

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0225. Min Act: -0.0006

Data Index: 1644882 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0235. Min Act: -0.0005

Data Index: 1416280 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0205. Min Act: -0.0006

Data Index: 1598596 (Python Code)

Max Activating Token Index: 661

Text #12

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0225. Min Act: -0.0006

Data Index: 1389677 (Python Code)

Max Activating Token Index: 392

Text #13

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1596048 (Python Code)

Max Activating Token Index: 678

Text #14

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0224. Min Act: -0.0006

Data Index: 1576615 (Python Code)

Max Activating Token Index: 525

Text #15

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0224. Min Act: -0.0006

Data Index: 1551632 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0244. Min Act: -0.0005

Data Index: 1476034 (Python Code)

Max Activating Token Index: 310

Text #17

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1594998 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1524603 (Python Code)

Max Activating Token Index: 972

Text #19

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1502915 (Python Code)

Max Activating Token Index: 838