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

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

Neuron 2200 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1559. Min Act: -0.0000

Data Index: 1364010 (Python Code)

Max Activating Token Index: 876

Text #1

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1393. Min Act: -0.0000

Data Index: 715748 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1347. Min Act: -0.0000

Data Index: 709140 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1288380 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1295. Min Act: -0.0000

Data Index: 380768 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1143. Min Act: -0.0000

Data Index: 1189666 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1247. Min Act: -0.0000

Data Index: 1274812 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1158. Min Act: -0.0000

Data Index: 580837 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1098431 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1119. Min Act: -0.0000

Data Index: 265784 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1068. Min Act: -0.0000

Data Index: 994421 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1074. Min Act: -0.0000

Data Index: 995961 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1093. Min Act: -0.0000

Data Index: 890691 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1088. Min Act: -0.0000

Data Index: 539707 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1156. Min Act: -0.0000

Data Index: 127421 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1310078 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1095. Min Act: -0.0000

Data Index: 558924 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1046. Min Act: -0.0000

Data Index: 536321 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1065. Min Act: -0.0000

Data Index: 233977 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 0.1559. Min Range: -0.1559

Max Act: 0.1054. Min Act: -0.0000

Data Index: 617262 (C4 (Web Text))

Max Activating Token Index: 87