Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 729 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0196. Min Act: -0.0006

Data Index: 1437291 (Python Code)

Max Activating Token Index: 749

Text #1

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0195. Min Act: -0.0006

Data Index: 1492862 (Python Code)

Max Activating Token Index: 551

Text #2

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1631422 (Python Code)

Max Activating Token Index: 543

Text #3

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1502915 (Python Code)

Max Activating Token Index: 967

Text #4

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0190. Min Act: -0.0006

Data Index: 1392860 (Python Code)

Max Activating Token Index: 938

Text #5

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1585896 (Python Code)

Max Activating Token Index: 30

Text #6

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1589969 (Python Code)

Max Activating Token Index: 264

Text #7

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1475869 (Python Code)

Max Activating Token Index: 600

Text #8

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0171. Min Act: -0.0006

Data Index: 1397986 (Python Code)

Max Activating Token Index: 1017

Text #9

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1609684 (Python Code)

Max Activating Token Index: 20

Text #10

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0173. Min Act: -0.0006

Data Index: 1496481 (Python Code)

Max Activating Token Index: 342

Text #11

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1579497 (Python Code)

Max Activating Token Index: 307

Text #12

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0173. Min Act: -0.0006

Data Index: 1637570 (Python Code)

Max Activating Token Index: 334

Text #13

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0169. Min Act: -0.0006

Data Index: 1366705 (Python Code)

Max Activating Token Index: 304

Text #14

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1430254 (Python Code)

Max Activating Token Index: 840

Text #15

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0180. Min Act: -0.0006

Data Index: 1621339 (Python Code)

Max Activating Token Index: 474

Text #16

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1523396 (Python Code)

Max Activating Token Index: 347

Text #17

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0176. Min Act: -0.0006

Data Index: 1528166 (Python Code)

Max Activating Token Index: 871

Text #18

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1521216 (Python Code)

Max Activating Token Index: 579

Text #19

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1493418 (Python Code)

Max Activating Token Index: 892