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

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

Neuron 67 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: 0.0872. Min Range: -0.0872

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1349555 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0872. Min Act: -0.0002

Data Index: 145079 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0836. Min Act: -0.0002

Data Index: 928412 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0805. Min Act: -0.0002

Data Index: 437776 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0802. Min Act: -0.0002

Data Index: 875816 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0786. Min Act: -0.0002

Data Index: 328756 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0770. Min Act: -0.0003

Data Index: 418287 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0783. Min Act: -0.0002

Data Index: 154381 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0781. Min Act: -0.0002

Data Index: 850131 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1012175 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1356746 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1468284 (Python Code)

Max Activating Token Index: 601

Text #12

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1174993 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1241902 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0763. Min Act: -0.0002

Data Index: 565356 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0759. Min Act: -0.0002

Data Index: 593662 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1585182 (Python Code)

Max Activating Token Index: 18

Text #17

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0746. Min Act: -0.0003

Data Index: 1208159 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0759. Min Act: -0.0002

Data Index: 456066 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1241819 (C4 (Web Text))

Max Activating Token Index: 111