Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4084 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0893. Min Act: -0.0002

Data Index: 229504 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0899. Min Act: -0.0001

Data Index: 461456 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0887. Min Act: -0.0001

Data Index: 610557 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1086772 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0885. Min Act: -0.0002

Data Index: 611547 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0879. Min Act: -0.0002

Data Index: 70901 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0846. Min Act: -0.0001

Data Index: 426004 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0863. Min Act: -0.0001

Data Index: 1155959 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0820. Min Act: -0.0002

Data Index: 952156 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0851. Min Act: -0.0001

Data Index: 921450 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0852. Min Act: -0.0002

Data Index: 635400 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0872. Min Act: -0.0002

Data Index: 564833 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0863. Min Act: -0.0002

Data Index: 876347 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1094072 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0777. Min Act: -0.0002

Data Index: 412698 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0810. Min Act: -0.0001

Data Index: 106722 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1304712 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1047505 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0810. Min Act: -0.0002

Data Index: 106339 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0808. Min Act: -0.0002

Data Index: 819374 (C4 (Web Text))

Max Activating Token Index: 168