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

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

Neuron 3522 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: 0.1144. Min Range: -0.1144

Max Act: 0.1144. Min Act: -0.0002

Data Index: 1473203 (Python Code)

Max Activating Token Index: 91

Text #1

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1067. Min Act: -0.0002

Data Index: 1484107 (Python Code)

Max Activating Token Index: 223

Text #2

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1056. Min Act: -0.0002

Data Index: 1382605 (Python Code)

Max Activating Token Index: 738

Text #3

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1480234 (Python Code)

Max Activating Token Index: 301

Text #4

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1458587 (Python Code)

Max Activating Token Index: 452

Text #5

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1653855 (Python Code)

Max Activating Token Index: 819

Text #6

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0937. Min Act: -0.0002

Data Index: 1636462 (Python Code)

Max Activating Token Index: 131

Text #7

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1378054 (Python Code)

Max Activating Token Index: 825

Text #8

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0908. Min Act: -0.0002

Data Index: 1612577 (Python Code)

Max Activating Token Index: 773

Text #9

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0939. Min Act: -0.0002

Data Index: 1600138 (Python Code)

Max Activating Token Index: 454

Text #10

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0917. Min Act: -0.0002

Data Index: 1644170 (Python Code)

Max Activating Token Index: 253

Text #11

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1535765 (Python Code)

Max Activating Token Index: 58

Text #12

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1455334 (Python Code)

Max Activating Token Index: 775

Text #13

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1037855 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0899. Min Act: -0.0002

Data Index: 1427062 (Python Code)

Max Activating Token Index: 704

Text #15

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0899. Min Act: -0.0002

Data Index: 1467380 (Python Code)

Max Activating Token Index: 31

Text #16

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1642912 (Python Code)

Max Activating Token Index: 180

Text #17

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1178020 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1553321 (Python Code)

Max Activating Token Index: 148

Text #19

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1629392 (Python Code)

Max Activating Token Index: 29