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

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

Neuron 1645 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2280. Min Act: -0.0002

Data Index: 1624039 (Python Code)

Max Activating Token Index: 459

Text #1

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2361. Min Act: -0.0002

Data Index: 1523510 (Python Code)

Max Activating Token Index: 729

Text #2

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2223. Min Act: -0.0002

Data Index: 1483519 (Python Code)

Max Activating Token Index: 895

Text #3

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2163. Min Act: -0.0002

Data Index: 1428615 (Python Code)

Max Activating Token Index: 19

Text #4

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2135. Min Act: -0.0002

Data Index: 1545295 (Python Code)

Max Activating Token Index: 998

Text #5

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2214. Min Act: -0.0002

Data Index: 1568684 (Python Code)

Max Activating Token Index: 776

Text #6

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2156. Min Act: -0.0002

Data Index: 1538895 (Python Code)

Max Activating Token Index: 157

Text #7

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2229. Min Act: -0.0002

Data Index: 1477311 (Python Code)

Max Activating Token Index: 222

Text #8

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2214. Min Act: -0.0002

Data Index: 1406242 (Python Code)

Max Activating Token Index: 713

Text #9

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2126. Min Act: -0.0001

Data Index: 1555981 (Python Code)

Max Activating Token Index: 234

Text #10

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2060. Min Act: -0.0002

Data Index: 1541239 (Python Code)

Max Activating Token Index: 789

Text #11

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2210. Min Act: -0.0002

Data Index: 1404893 (Python Code)

Max Activating Token Index: 689

Text #12

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2147. Min Act: -0.0001

Data Index: 1362337 (Python Code)

Max Activating Token Index: 248

Text #13

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1990. Min Act: -0.0002

Data Index: 1581737 (Python Code)

Max Activating Token Index: 445

Text #14

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2150. Min Act: -0.0002

Data Index: 1533526 (Python Code)

Max Activating Token Index: 543

Text #15

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2040. Min Act: -0.0002

Data Index: 1518432 (Python Code)

Max Activating Token Index: 49

Text #16

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2099. Min Act: -0.0002

Data Index: 1549923 (Python Code)

Max Activating Token Index: 386

Text #17

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2073. Min Act: -0.0002

Data Index: 1589108 (Python Code)

Max Activating Token Index: 883

Text #18

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2181. Min Act: -0.0002

Data Index: 1377469 (Python Code)

Max Activating Token Index: 131

Text #19

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2074. Min Act: -0.0002

Data Index: 1501605 (Python Code)

Max Activating Token Index: 31