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

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

Neuron 354 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: 0.0284. Min Range: -0.0284

Max Act: 0.0284. Min Act: -0.0006

Data Index: 1365407 (Python Code)

Max Activating Token Index: 33

Text #1

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0274. Min Act: -0.0006

Data Index: 1651396 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0278. Min Act: -0.0006

Data Index: 1404081 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0278. Min Act: -0.0006

Data Index: 1578452 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0271. Min Act: -0.0006

Data Index: 1502801 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0267. Min Act: -0.0006

Data Index: 836518 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0254. Min Act: -0.0006

Data Index: 1480675 (Python Code)

Max Activating Token Index: 747

Text #7

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1585118 (Python Code)

Max Activating Token Index: 23

Text #8

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1425397 (Python Code)

Max Activating Token Index: 74

Text #9

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0260. Min Act: -0.0006

Data Index: 1504696 (Python Code)

Max Activating Token Index: 208

Text #10

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1604025 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1585626 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1525866 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1458114 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1426945 (Python Code)

Max Activating Token Index: 382

Text #15

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0253. Min Act: -0.0006

Data Index: 1435945 (Python Code)

Max Activating Token Index: 267

Text #16

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1439940 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1443629 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1455501 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1606541 (Python Code)

Max Activating Token Index: 4