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

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

Neuron 3297 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: 0.1187. Min Range: -0.1187

Max Act: 0.1187. Min Act: -0.0002

Data Index: 1649308 (Python Code)

Max Activating Token Index: 625

Text #1

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1158. Min Act: -0.0002

Data Index: 1615554 (Python Code)

Max Activating Token Index: 43

Text #2

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1146. Min Act: -0.0002

Data Index: 1625641 (Python Code)

Max Activating Token Index: 214

Text #3

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1062. Min Act: -0.0002

Data Index: 1579641 (Python Code)

Max Activating Token Index: 648

Text #4

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1037. Min Act: -0.0002

Data Index: 1371671 (Python Code)

Max Activating Token Index: 868

Text #5

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1005. Min Act: -0.0002

Data Index: 1380162 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0984. Min Act: -0.0002

Data Index: 1433113 (Python Code)

Max Activating Token Index: 259

Text #7

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0998. Min Act: -0.0002

Data Index: 1459120 (Python Code)

Max Activating Token Index: 186

Text #8

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0988. Min Act: -0.0002

Data Index: 1412289 (Python Code)

Max Activating Token Index: 277

Text #9

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0964. Min Act: -0.0002

Data Index: 1547319 (Python Code)

Max Activating Token Index: 700

Text #10

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1623424 (Python Code)

Max Activating Token Index: 808

Text #11

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1558939 (Python Code)

Max Activating Token Index: 450

Text #12

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1535372 (Python Code)

Max Activating Token Index: 888

Text #13

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0935. Min Act: -0.0002

Data Index: 1397300 (Python Code)

Max Activating Token Index: 720

Text #14

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1603687 (Python Code)

Max Activating Token Index: 51

Text #15

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1455099 (Python Code)

Max Activating Token Index: 192

Text #16

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1496783 (Python Code)

Max Activating Token Index: 645

Text #17

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0924. Min Act: -0.0002

Data Index: 1474796 (Python Code)

Max Activating Token Index: 33

Text #18

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0921. Min Act: -0.0002

Data Index: 1655395 (Python Code)

Max Activating Token Index: 675

Text #19

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1649990 (Python Code)

Max Activating Token Index: 220