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

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

Neuron 716 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1295. Min Act: -0.0002

Data Index: 1380796 (Python Code)

Max Activating Token Index: 53

Text #1

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1233. Min Act: -0.0002

Data Index: 1543204 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1192. Min Act: -0.0002

Data Index: 1625303 (Python Code)

Max Activating Token Index: 73

Text #3

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1169. Min Act: -0.0002

Data Index: 1618867 (Python Code)

Max Activating Token Index: 355

Text #4

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1185. Min Act: -0.0002

Data Index: 1516227 (Python Code)

Max Activating Token Index: 102

Text #5

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1142. Min Act: -0.0002

Data Index: 1537270 (Python Code)

Max Activating Token Index: 75

Text #6

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1119. Min Act: -0.0002

Data Index: 1409542 (Python Code)

Max Activating Token Index: 397

Text #7

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1537535 (Python Code)

Max Activating Token Index: 417

Text #8

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1115. Min Act: -0.0002

Data Index: 1559279 (Python Code)

Max Activating Token Index: 36

Text #9

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1111. Min Act: -0.0002

Data Index: 1505848 (Python Code)

Max Activating Token Index: 108

Text #10

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1132. Min Act: -0.0002

Data Index: 1381300 (Python Code)

Max Activating Token Index: 366

Text #11

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1101. Min Act: -0.0002

Data Index: 1494739 (Python Code)

Max Activating Token Index: 185

Text #12

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1486971 (Python Code)

Max Activating Token Index: 260

Text #13

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1643274 (Python Code)

Max Activating Token Index: 102

Text #14

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1573614 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1092. Min Act: -0.0002

Data Index: 1248253 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1087. Min Act: -0.0002

Data Index: 1496549 (Python Code)

Max Activating Token Index: 260

Text #17

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1090. Min Act: -0.0002

Data Index: 1595330 (Python Code)

Max Activating Token Index: 105

Text #18

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1088. Min Act: -0.0002

Data Index: 1470747 (Python Code)

Max Activating Token Index: 405

Text #19

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1535972 (Python Code)

Max Activating Token Index: 168