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

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

Neuron 1688 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1449388 (Python Code)

Max Activating Token Index: 123

Text #1

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1277491 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0002

Data Index: 869228 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0115. Min Act: -0.0002

Data Index: 680888 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0002

Data Index: 254279 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0002

Data Index: 412312 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1002796 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1560114 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0102. Min Act: -0.0002

Data Index: 209183 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0102. Min Act: -0.0002

Data Index: 1469440 (Python Code)

Max Activating Token Index: 46

Text #10

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0104. Min Act: -0.0002

Data Index: 753765 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1484609 (Python Code)

Max Activating Token Index: 76

Text #12

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0100. Min Act: -0.0002

Data Index: 1335574 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1437289 (Python Code)

Max Activating Token Index: 29

Text #14

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0097. Min Act: -0.0002

Data Index: 717263 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0099. Min Act: -0.0002

Data Index: 1648051 (Python Code)

Max Activating Token Index: 17

Text #16

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0099. Min Act: -0.0002

Data Index: 524679 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1215044 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0097. Min Act: -0.0002

Data Index: 17808 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0095. Min Act: -0.0002

Data Index: 1622063 (Python Code)

Max Activating Token Index: 6