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

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

Neuron 1506 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: 0.0218. Min Range: -0.0218

Max Act: 0.0208. Min Act: -0.0006

Data Index: 1641646 (Python Code)

Max Activating Token Index: 744

Text #1

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0215. Min Act: -0.0006

Data Index: 1585752 (Python Code)

Max Activating Token Index: 458

Text #2

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1545791 (Python Code)

Max Activating Token Index: 420

Text #3

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1553919 (Python Code)

Max Activating Token Index: 573

Text #4

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0206. Min Act: -0.0006

Data Index: 1487733 (Python Code)

Max Activating Token Index: 242

Text #5

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0205. Min Act: -0.0006

Data Index: 1524383 (Python Code)

Max Activating Token Index: 441

Text #6

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1545220 (Python Code)

Max Activating Token Index: 451

Text #7

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0203. Min Act: -0.0006

Data Index: 1600800 (Python Code)

Max Activating Token Index: 161

Text #8

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0203. Min Act: -0.0006

Data Index: 1522877 (Python Code)

Max Activating Token Index: 700

Text #9

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0195. Min Act: -0.0006

Data Index: 1427453 (Python Code)

Max Activating Token Index: 660

Text #10

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0202. Min Act: -0.0006

Data Index: 1598755 (Python Code)

Max Activating Token Index: 609

Text #11

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0203. Min Act: -0.0006

Data Index: 1469386 (Python Code)

Max Activating Token Index: 468

Text #12

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1459351 (Python Code)

Max Activating Token Index: 393

Text #13

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0200. Min Act: -0.0006

Data Index: 1426026 (Python Code)

Max Activating Token Index: 680

Text #14

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0196. Min Act: -0.0006

Data Index: 1441874 (Python Code)

Max Activating Token Index: 81

Text #15

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1480202 (Python Code)

Max Activating Token Index: 130

Text #16

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0206. Min Act: -0.0006

Data Index: 1394349 (Python Code)

Max Activating Token Index: 237

Text #17

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0195. Min Act: -0.0006

Data Index: 1599284 (Python Code)

Max Activating Token Index: 330

Text #18

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0204. Min Act: -0.0006

Data Index: 1482143 (Python Code)

Max Activating Token Index: 366

Text #19

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0191. Min Act: -0.0006

Data Index: 1539529 (Python Code)

Max Activating Token Index: 829