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

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

Neuron 3195 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: 0.0131. Min Range: -0.0131

Max Act: 0.0131. Min Act: -0.0002

Data Index: 636882 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0124. Min Act: -0.0002

Data Index: 83908 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0105. Min Act: -0.0002

Data Index: 364200 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0113. Min Act: -0.0002

Data Index: 712015 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0108. Min Act: -0.0002

Data Index: 325177 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0083. Min Act: -0.0002

Data Index: 1105471 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0107. Min Act: -0.0002

Data Index: 1520744 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0107. Min Act: -0.0002

Data Index: 867633 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0098. Min Act: -0.0002

Data Index: 547907 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0090. Min Act: -0.0002

Data Index: 745160 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0098. Min Act: -0.0002

Data Index: 436123 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0104. Min Act: -0.0002

Data Index: 334799 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0101. Min Act: -0.0002

Data Index: 695302 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1524619 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0097. Min Act: -0.0002

Data Index: 232839 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0095. Min Act: -0.0002

Data Index: 431655 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0092. Min Act: -0.0002

Data Index: 19897 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0098. Min Act: -0.0002

Data Index: 285022 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1313268 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1237616 (C4 (Web Text))

Max Activating Token Index: 112