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

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

Neuron 4596 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: 0.1123. Min Range: -0.1123

Max Act: 0.1123. Min Act: -0.0002

Data Index: 1589695 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.1002. Min Act: -0.0002

Data Index: 1524260 (Python Code)

Max Activating Token Index: 96

Text #2

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.1000. Min Act: -0.0002

Data Index: 1461261 (Python Code)

Max Activating Token Index: 168

Text #3

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0957. Min Act: -0.0002

Data Index: 277773 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0939. Min Act: -0.0002

Data Index: 1380239 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0939. Min Act: -0.0002

Data Index: 1350893 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0938. Min Act: -0.0002

Data Index: 1531416 (Python Code)

Max Activating Token Index: 137

Text #7

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0917. Min Act: -0.0002

Data Index: 1560032 (Python Code)

Max Activating Token Index: 136

Text #8

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0914. Min Act: -0.0002

Data Index: 881426 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1468143 (Python Code)

Max Activating Token Index: 125

Text #10

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0905. Min Act: -0.0002

Data Index: 1633888 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0909. Min Act: -0.0002

Data Index: 1567091 (Python Code)

Max Activating Token Index: 75

Text #12

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1567424 (Python Code)

Max Activating Token Index: 192

Text #13

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1483915 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1649652 (Python Code)

Max Activating Token Index: 366

Text #15

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0871. Min Act: -0.0002

Data Index: 700686 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0859. Min Act: -0.0002

Data Index: 1636485 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1473243 (Python Code)

Max Activating Token Index: 352

Text #18

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1525133 (Python Code)

Max Activating Token Index: 237

Text #19

Max Range: 0.1123. Min Range: -0.1123

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1463973 (Python Code)

Max Activating Token Index: 161