Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 732 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1622501 (Python Code)

Max Activating Token Index: 705

Text #1

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1406977 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0181. Min Act: -0.0002

Data Index: 399058 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0180. Min Act: -0.0002

Data Index: 1401903 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0180. Min Act: -0.0002

Data Index: 1520181 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1627691 (Python Code)

Max Activating Token Index: 399

Text #6

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0174. Min Act: -0.0002

Data Index: 713436 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1581691 (Python Code)

Max Activating Token Index: 32

Text #8

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1521901 (Python Code)

Max Activating Token Index: 467

Text #9

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0172. Min Act: -0.0002

Data Index: 659335 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1485400 (Python Code)

Max Activating Token Index: 123

Text #11

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1420627 (Python Code)

Max Activating Token Index: 576

Text #12

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1612362 (Python Code)

Max Activating Token Index: 105

Text #13

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1413574 (Python Code)

Max Activating Token Index: 29

Text #14

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0168. Min Act: -0.0002

Data Index: 277312 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1607060 (Python Code)

Max Activating Token Index: 61

Text #16

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0166. Min Act: -0.0001

Data Index: 1622947 (Python Code)

Max Activating Token Index: 194

Text #17

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0166. Min Act: -0.0001

Data Index: 1534776 (Python Code)

Max Activating Token Index: 903

Text #18

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1560658 (Python Code)

Max Activating Token Index: 322

Text #19

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1602704 (Python Code)

Max Activating Token Index: 20