Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1540 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0044. Min Act: -0.0003

Data Index: 1632582 (Python Code)

Max Activating Token Index: 187

Text #1

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0043. Min Act: -0.0003

Data Index: 1634295 (Python Code)

Max Activating Token Index: 67

Text #2

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0042. Min Act: -0.0003

Data Index: 1369810 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0040. Min Act: -0.0003

Data Index: 1382410 (Python Code)

Max Activating Token Index: 92

Text #4

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0040. Min Act: -0.0003

Data Index: 1415419 (Python Code)

Max Activating Token Index: 80

Text #5

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0037. Min Act: -0.0003

Data Index: 1498583 (Python Code)

Max Activating Token Index: 188

Text #6

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0037. Min Act: -0.0004

Data Index: 1441860 (Python Code)

Max Activating Token Index: 103

Text #7

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0037. Min Act: -0.0003

Data Index: 1543901 (Python Code)

Max Activating Token Index: 125

Text #8

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1460557 (Python Code)

Max Activating Token Index: 333

Text #9

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1644758 (Python Code)

Max Activating Token Index: 165

Text #10

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1558438 (Python Code)

Max Activating Token Index: 46

Text #11

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1365803 (Python Code)

Max Activating Token Index: 219

Text #12

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1563254 (Python Code)

Max Activating Token Index: 59

Text #13

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1515418 (Python Code)

Max Activating Token Index: 71

Text #14

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1636554 (Python Code)

Max Activating Token Index: 41

Text #15

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0033. Min Act: -0.0003

Data Index: 1430592 (Python Code)

Max Activating Token Index: 169

Text #16

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0033. Min Act: -0.0003

Data Index: 1458835 (Python Code)

Max Activating Token Index: 113

Text #17

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0034. Min Act: -0.0003

Data Index: 1435418 (Python Code)

Max Activating Token Index: 78

Text #18

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0033. Min Act: -0.0003

Data Index: 1368433 (Python Code)

Max Activating Token Index: 188

Text #19

Max Range: 0.0044. Min Range: -0.0044

Max Act: 0.0032. Min Act: -0.0003

Data Index: 1480831 (Python Code)

Max Activating Token Index: 693