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

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

Neuron 527 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1758. Min Act: -0.0002

Data Index: 1313375 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1483. Min Act: -0.0002

Data Index: 32815 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1196. Min Act: -0.0002

Data Index: 1077544 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1174. Min Act: -0.0002

Data Index: 909334 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1205. Min Act: -0.0002

Data Index: 644164 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1163. Min Act: -0.0002

Data Index: 1267488 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1134. Min Act: -0.0002

Data Index: 942755 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1592953 (Python Code)

Max Activating Token Index: 907

Text #8

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1162. Min Act: -0.0002

Data Index: 1270202 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1046. Min Act: -0.0002

Data Index: 156145 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1052. Min Act: -0.0002

Data Index: 1469185 (Python Code)

Max Activating Token Index: 217

Text #11

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1046. Min Act: -0.0002

Data Index: 634670 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1107. Min Act: -0.0002

Data Index: 865848 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1026. Min Act: -0.0002

Data Index: 235679 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1031. Min Act: -0.0002

Data Index: 548838 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.0984. Min Act: -0.0002

Data Index: 1467514 (Python Code)

Max Activating Token Index: 260

Text #16

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1147548 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.0925. Min Act: -0.0002

Data Index: 622672 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1024. Min Act: -0.0002

Data Index: 822612 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.1758. Min Range: -0.1758

Max Act: 0.1089. Min Act: -0.0002

Data Index: 76302 (C4 (Web Text))

Max Activating Token Index: 597