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

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

Neuron 5806 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1171. Min Act: -0.0002

Data Index: 1529385 (Python Code)

Max Activating Token Index: 938

Text #1

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1388613 (Python Code)

Max Activating Token Index: 259

Text #2

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1535101 (Python Code)

Max Activating Token Index: 152

Text #3

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0119. Min Act: -0.0002

Data Index: 1501516 (Python Code)

Max Activating Token Index: 182

Text #4

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0119. Min Act: -0.0002

Data Index: 1475263 (Python Code)

Max Activating Token Index: 128

Text #5

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1410201 (Python Code)

Max Activating Token Index: 186

Text #6

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0102. Min Act: -0.0002

Data Index: 1560959 (Python Code)

Max Activating Token Index: 63

Text #7

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0099. Min Act: -0.0002

Data Index: 1525869 (Python Code)

Max Activating Token Index: 63

Text #8

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0098. Min Act: -0.0002

Data Index: 802573 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0100. Min Act: -0.0002

Data Index: 1637990 (Python Code)

Max Activating Token Index: 113

Text #10

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0101. Min Act: -0.0002

Data Index: 1577565 (Python Code)

Max Activating Token Index: 103

Text #11

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1628232 (Python Code)

Max Activating Token Index: 111

Text #12

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1624086 (Python Code)

Max Activating Token Index: 56

Text #13

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0077. Min Act: -0.0002

Data Index: 1428222 (Python Code)

Max Activating Token Index: 614

Text #14

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1545804 (Python Code)

Max Activating Token Index: 107

Text #15

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0098. Min Act: -0.0002

Data Index: 1522402 (Python Code)

Max Activating Token Index: 116

Text #16

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0095. Min Act: -0.0002

Data Index: 1553193 (Python Code)

Max Activating Token Index: 95

Text #17

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1413055 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1501555 (Python Code)

Max Activating Token Index: 102

Text #19

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0094. Min Act: -0.0002

Data Index: 1634386 (Python Code)

Max Activating Token Index: 119