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

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

Neuron 3464 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1467. Min Act: -0.0000

Data Index: 600916 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1266. Min Act: -0.0000

Data Index: 1026919 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1263. Min Act: -0.0000

Data Index: 804829 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1160. Min Act: -0.0000

Data Index: 197546 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1139. Min Act: -0.0000

Data Index: 8048 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1176. Min Act: -0.0000

Data Index: 1067035 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1161. Min Act: -0.0000

Data Index: 257408 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1342116 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1332538 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1110. Min Act: -0.0000

Data Index: 834148 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1180. Min Act: -0.0000

Data Index: 132604 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1351193 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1067. Min Act: -0.0000

Data Index: 882774 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1009. Min Act: -0.0000

Data Index: 845743 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1039. Min Act: -0.0000

Data Index: 1062212 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1033. Min Act: -0.0000

Data Index: 139214 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1043. Min Act: -0.0000

Data Index: 92810 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.1071. Min Act: -0.0000

Data Index: 833429 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0998. Min Act: -0.0000

Data Index: 347330 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0997. Min Act: -0.0000

Data Index: 238765 (C4 (Web Text))

Max Activating Token Index: 221