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

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

Neuron 3072 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: 0.1099. Min Range: -0.1099

Max Act: 0.1099. Min Act: -0.0002

Data Index: 93458 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.1053. Min Act: -0.0002

Data Index: 732898 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.1022. Min Act: -0.0002

Data Index: 1305734 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.1005. Min Act: -0.0002

Data Index: 119655 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0997. Min Act: -0.0002

Data Index: 463462 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0974. Min Act: -0.0002

Data Index: 90105 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0935. Min Act: -0.0002

Data Index: 311352 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0937. Min Act: -0.0002

Data Index: 62886 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1248081 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0894. Min Act: -0.0002

Data Index: 378749 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0911. Min Act: -0.0002

Data Index: 550125 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0899. Min Act: -0.0002

Data Index: 130279 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0909. Min Act: -0.0002

Data Index: 128005 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0903. Min Act: -0.0002

Data Index: 408383 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0913. Min Act: -0.0002

Data Index: 586834 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0865. Min Act: -0.0002

Data Index: 868248 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0845. Min Act: -0.0002

Data Index: 25360 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0862. Min Act: -0.0002

Data Index: 765940 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0878. Min Act: -0.0002

Data Index: 540480 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1018598 (C4 (Web Text))

Max Activating Token Index: 899