Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 743 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0221. Min Act: -0.0004

Data Index: 1432343 (Python Code)

Max Activating Token Index: 483

Text #1

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0217. Min Act: -0.0004

Data Index: 1176788 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0202. Min Act: -0.0004

Data Index: 1651545 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0202. Min Act: -0.0004

Data Index: 1581794 (Python Code)

Max Activating Token Index: 766

Text #4

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0202. Min Act: -0.0004

Data Index: 1532548 (Python Code)

Max Activating Token Index: 465

Text #5

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0196. Min Act: -0.0004

Data Index: 702640 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0199. Min Act: -0.0004

Data Index: 748430 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0191. Min Act: -0.0004

Data Index: 1004838 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0185. Min Act: -0.0004

Data Index: 1415257 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0172. Min Act: -0.0004

Data Index: 296908 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0174. Min Act: -0.0004

Data Index: 1379789 (Python Code)

Max Activating Token Index: 637

Text #11

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0171. Min Act: -0.0004

Data Index: 299360 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0173. Min Act: -0.0004

Data Index: 1585309 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0189. Min Act: -0.0004

Data Index: 261119 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0169. Min Act: -0.0004

Data Index: 1632823 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0168. Min Act: -0.0004

Data Index: 1588685 (Python Code)

Max Activating Token Index: 987

Text #16

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0171. Min Act: -0.0004

Data Index: 1486124 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0159. Min Act: -0.0004

Data Index: 1380434 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0154. Min Act: -0.0004

Data Index: 1405256 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0153. Min Act: -0.0004

Data Index: 673627 (C4 (Web Text))

Max Activating Token Index: 800