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

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

Neuron 3299 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1253. Min Act: -0.0002

Data Index: 1367189 (Python Code)

Max Activating Token Index: 843

Text #1

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1127. Min Act: -0.0002

Data Index: 1366093 (Python Code)

Max Activating Token Index: 196

Text #2

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1170. Min Act: -0.0002

Data Index: 1405319 (Python Code)

Max Activating Token Index: 150

Text #3

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1133. Min Act: -0.0002

Data Index: 1472427 (Python Code)

Max Activating Token Index: 429

Text #4

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1212. Min Act: -0.0002

Data Index: 1403998 (Python Code)

Max Activating Token Index: 904

Text #5

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1160. Min Act: -0.0002

Data Index: 1566692 (Python Code)

Max Activating Token Index: 546

Text #6

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1137. Min Act: -0.0002

Data Index: 1641988 (Python Code)

Max Activating Token Index: 248

Text #7

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1115. Min Act: -0.0002

Data Index: 1459998 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1121. Min Act: -0.0002

Data Index: 1492428 (Python Code)

Max Activating Token Index: 845

Text #9

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1128. Min Act: -0.0002

Data Index: 1366874 (Python Code)

Max Activating Token Index: 447

Text #10

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1037. Min Act: -0.0002

Data Index: 1475903 (Python Code)

Max Activating Token Index: 276

Text #11

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1065. Min Act: -0.0002

Data Index: 1542435 (Python Code)

Max Activating Token Index: 632

Text #12

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1133. Min Act: -0.0002

Data Index: 1593412 (Python Code)

Max Activating Token Index: 307

Text #13

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1045. Min Act: -0.0002

Data Index: 1587552 (Python Code)

Max Activating Token Index: 690

Text #14

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1047. Min Act: -0.0002

Data Index: 1632566 (Python Code)

Max Activating Token Index: 525

Text #15

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1066. Min Act: -0.0002

Data Index: 1617110 (Python Code)

Max Activating Token Index: 643

Text #16

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1041. Min Act: -0.0002

Data Index: 1481290 (Python Code)

Max Activating Token Index: 54

Text #17

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1399914 (Python Code)

Max Activating Token Index: 688

Text #18

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1110. Min Act: -0.0002

Data Index: 1515732 (Python Code)

Max Activating Token Index: 397

Text #19

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1386533 (Python Code)

Max Activating Token Index: 875