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

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

Neuron 4606 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: 0.1023. Min Range: -0.1023

Max Act: 0.1009. Min Act: -0.0002

Data Index: 693810 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.1023. Min Act: -0.0002

Data Index: 833701 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0962. Min Act: -0.0002

Data Index: 763109 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0952. Min Act: -0.0002

Data Index: 618165 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0942. Min Act: -0.0002

Data Index: 605182 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1179022 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0877. Min Act: -0.0002

Data Index: 748499 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0890. Min Act: -0.0002

Data Index: 803561 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0867. Min Act: -0.0002

Data Index: 962291 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0857. Min Act: -0.0002

Data Index: 986327 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0863. Min Act: -0.0002

Data Index: 992570 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0825. Min Act: -0.0002

Data Index: 222536 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0809. Min Act: -0.0002

Data Index: 83764 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0821. Min Act: -0.0002

Data Index: 386605 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0809. Min Act: -0.0002

Data Index: 386957 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0811. Min Act: -0.0002

Data Index: 209249 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1175232 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0812. Min Act: -0.0002

Data Index: 214518 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0789. Min Act: -0.0002

Data Index: 834289 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0785. Min Act: -0.0002

Data Index: 56702 (C4 (Web Text))

Max Activating Token Index: 644