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

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

Neuron 1003 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0277. Min Act: -0.0006

Data Index: 1614504 (Python Code)

Max Activating Token Index: 994

Text #1

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0276. Min Act: -0.0006

Data Index: 1481577 (Python Code)

Max Activating Token Index: 1009

Text #2

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0276. Min Act: -0.0006

Data Index: 1490437 (Python Code)

Max Activating Token Index: 351

Text #3

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0284. Min Act: -0.0006

Data Index: 1468897 (Python Code)

Max Activating Token Index: 725

Text #4

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0283. Min Act: -0.0006

Data Index: 1652448 (Python Code)

Max Activating Token Index: 970

Text #5

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0270. Min Act: -0.0006

Data Index: 1653596 (Python Code)

Max Activating Token Index: 967

Text #6

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1466910 (Python Code)

Max Activating Token Index: 348

Text #7

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0252. Min Act: -0.0006

Data Index: 1461544 (Python Code)

Max Activating Token Index: 383

Text #8

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1479979 (Python Code)

Max Activating Token Index: 408

Text #9

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0254. Min Act: -0.0006

Data Index: 1643588 (Python Code)

Max Activating Token Index: 153

Text #10

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0253. Min Act: -0.0006

Data Index: 1559797 (Python Code)

Max Activating Token Index: 552

Text #11

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1483030 (Python Code)

Max Activating Token Index: 867

Text #12

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0254. Min Act: -0.0006

Data Index: 1629220 (Python Code)

Max Activating Token Index: 349

Text #13

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0246. Min Act: -0.0005

Data Index: 1431277 (Python Code)

Max Activating Token Index: 684

Text #14

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1604835 (Python Code)

Max Activating Token Index: 67

Text #15

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1503701 (Python Code)

Max Activating Token Index: 739

Text #16

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1482053 (Python Code)

Max Activating Token Index: 249

Text #17

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1536816 (Python Code)

Max Activating Token Index: 870

Text #18

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1416183 (Python Code)

Max Activating Token Index: 71

Text #19

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1506716 (Python Code)

Max Activating Token Index: 860