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

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

Neuron 2544 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: 0.0079. Min Range: -0.0079

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1473962 (Python Code)

Max Activating Token Index: 107

Text #1

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1592704 (Python Code)

Max Activating Token Index: 139

Text #2

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0078. Min Act: -0.0003

Data Index: 1616221 (Python Code)

Max Activating Token Index: 162

Text #3

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1426625 (Python Code)

Max Activating Token Index: 129

Text #4

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0076. Min Act: -0.0003

Data Index: 1599490 (Python Code)

Max Activating Token Index: 122

Text #5

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1431658 (Python Code)

Max Activating Token Index: 160

Text #6

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1611576 (Python Code)

Max Activating Token Index: 162

Text #7

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1422014 (Python Code)

Max Activating Token Index: 199

Text #8

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0074. Min Act: -0.0003

Data Index: 1456923 (Python Code)

Max Activating Token Index: 107

Text #9

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0074. Min Act: -0.0003

Data Index: 1425410 (Python Code)

Max Activating Token Index: 93

Text #10

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0074. Min Act: -0.0003

Data Index: 1600692 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1425580 (Python Code)

Max Activating Token Index: 169

Text #12

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0074. Min Act: -0.0003

Data Index: 1433794 (Python Code)

Max Activating Token Index: 138

Text #13

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1606146 (Python Code)

Max Activating Token Index: 179

Text #14

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1442183 (Python Code)

Max Activating Token Index: 189

Text #15

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1506568 (Python Code)

Max Activating Token Index: 143

Text #16

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1555412 (Python Code)

Max Activating Token Index: 120

Text #17

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1423136 (Python Code)

Max Activating Token Index: 150

Text #18

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1453973 (Python Code)

Max Activating Token Index: 115

Text #19

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1638044 (Python Code)

Max Activating Token Index: 189