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

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

Neuron 1640 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.3225. Min Act: -0.0000

Data Index: 242357 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1184. Min Act: -0.0000

Data Index: 1554856 (Python Code)

Max Activating Token Index: 276

Text #2

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1069. Min Act: -0.0000

Data Index: 910246 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1440296 (Python Code)

Max Activating Token Index: 334

Text #4

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1281. Min Act: -0.0000

Data Index: 1639745 (Python Code)

Max Activating Token Index: 476

Text #5

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1306. Min Act: -0.0000

Data Index: 1436224 (Python Code)

Max Activating Token Index: 288

Text #6

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1552018 (Python Code)

Max Activating Token Index: 404

Text #7

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1390. Min Act: -0.0000

Data Index: 1361842 (Python Code)

Max Activating Token Index: 341

Text #8

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1505360 (Python Code)

Max Activating Token Index: 211

Text #9

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1482907 (Python Code)

Max Activating Token Index: 106

Text #10

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1186. Min Act: -0.0000

Data Index: 1406777 (Python Code)

Max Activating Token Index: 315

Text #11

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1439874 (Python Code)

Max Activating Token Index: 307

Text #12

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1267. Min Act: -0.0000

Data Index: 1647439 (Python Code)

Max Activating Token Index: 251

Text #13

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1608590 (Python Code)

Max Activating Token Index: 182

Text #14

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1251. Min Act: -0.0000

Data Index: 1497572 (Python Code)

Max Activating Token Index: 241

Text #15

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1535958 (Python Code)

Max Activating Token Index: 225

Text #16

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1277. Min Act: -0.0000

Data Index: 1607628 (Python Code)

Max Activating Token Index: 107

Text #17

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1470805 (Python Code)

Max Activating Token Index: 550

Text #18

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1216. Min Act: -0.0000

Data Index: 1370370 (Python Code)

Max Activating Token Index: 456

Text #19

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1311. Min Act: -0.0000

Data Index: 1484491 (Python Code)

Max Activating Token Index: 244