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

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

Neuron 473 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1374621 (Python Code)

Max Activating Token Index: 306

Text #1

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1269. Min Act: -0.0001

Data Index: 1391729 (Python Code)

Max Activating Token Index: 139

Text #2

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1182. Min Act: -0.0001

Data Index: 1581642 (Python Code)

Max Activating Token Index: 780

Text #3

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1368475 (Python Code)

Max Activating Token Index: 233

Text #4

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1190. Min Act: -0.0001

Data Index: 1594326 (Python Code)

Max Activating Token Index: 413

Text #5

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1483338 (Python Code)

Max Activating Token Index: 343

Text #6

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1585333 (Python Code)

Max Activating Token Index: 574

Text #7

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1514145 (Python Code)

Max Activating Token Index: 574

Text #8

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1041. Min Act: -0.0001

Data Index: 1519357 (Python Code)

Max Activating Token Index: 863

Text #9

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1161. Min Act: -0.0001

Data Index: 1578943 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1509469 (Python Code)

Max Activating Token Index: 446

Text #11

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1408918 (Python Code)

Max Activating Token Index: 29

Text #12

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1070. Min Act: -0.0001

Data Index: 1408745 (Python Code)

Max Activating Token Index: 91

Text #13

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0995. Min Act: -0.0001

Data Index: 1391159 (Python Code)

Max Activating Token Index: 719

Text #14

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1479090 (Python Code)

Max Activating Token Index: 659

Text #15

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1384130 (Python Code)

Max Activating Token Index: 436

Text #16

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1645612 (Python Code)

Max Activating Token Index: 17

Text #17

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1407512 (Python Code)

Max Activating Token Index: 456

Text #18

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1050. Min Act: -0.0001

Data Index: 1398001 (Python Code)

Max Activating Token Index: 75

Text #19

Max Range: 0.1269. Min Range: -0.1269

Max Act: 0.1134. Min Act: -0.0001

Data Index: 1437726 (Python Code)

Max Activating Token Index: 662