Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 861 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0040. Min Act: -0.0005

Data Index: 1486154 (Python Code)

Max Activating Token Index: 71

Text #1

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0034. Min Act: -0.0005

Data Index: 1375445 (Python Code)

Max Activating Token Index: 132

Text #2

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0033. Min Act: -0.0005

Data Index: 1586410 (Python Code)

Max Activating Token Index: 100

Text #3

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1468792 (Python Code)

Max Activating Token Index: 139

Text #4

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1472282 (Python Code)

Max Activating Token Index: 110

Text #5

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0033. Min Act: -0.0005

Data Index: 1492777 (Python Code)

Max Activating Token Index: 281

Text #6

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0031. Min Act: -0.0005

Data Index: 969159 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0031. Min Act: -0.0005

Data Index: 395282 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0030. Min Act: -0.0005

Data Index: 1421076 (Python Code)

Max Activating Token Index: 45

Text #9

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1615712 (Python Code)

Max Activating Token Index: 197

Text #10

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1511993 (Python Code)

Max Activating Token Index: 80

Text #11

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0030. Min Act: -0.0005

Data Index: 1260533 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0030. Min Act: -0.0005

Data Index: 1591620 (Python Code)

Max Activating Token Index: 109

Text #13

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0030. Min Act: -0.0005

Data Index: 993378 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0030. Min Act: -0.0005

Data Index: 209990 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0029. Min Act: -0.0005

Data Index: 197873 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0030. Min Act: -0.0005

Data Index: 1531430 (Python Code)

Max Activating Token Index: 94

Text #17

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0029. Min Act: -0.0005

Data Index: 601569 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0030. Min Act: -0.0005

Data Index: 1560766 (Python Code)

Max Activating Token Index: 180

Text #19

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0029. Min Act: -0.0005

Data Index: 1383253 (Python Code)

Max Activating Token Index: 61