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

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

Neuron 3533 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: 0.0929. Min Range: -0.0929

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1119488 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0872. Min Act: -0.0002

Data Index: 184181 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0855. Min Act: -0.0002

Data Index: 452128 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0850. Min Act: -0.0002

Data Index: 1519286 (Python Code)

Max Activating Token Index: 530

Text #4

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0799. Min Act: -0.0002

Data Index: 109163 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1281329 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0761. Min Act: -0.0002

Data Index: 857748 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0750. Min Act: -0.0002

Data Index: 453193 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0752. Min Act: -0.0002

Data Index: 692829 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0754. Min Act: -0.0002

Data Index: 24105 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0744. Min Act: -0.0002

Data Index: 754626 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0736. Min Act: -0.0002

Data Index: 128915 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0727. Min Act: -0.0002

Data Index: 336588 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0740. Min Act: -0.0002

Data Index: 359931 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0731. Min Act: -0.0002

Data Index: 111731 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1301896 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0720. Min Act: -0.0002

Data Index: 97637 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0712. Min Act: -0.0002

Data Index: 1040265 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0716. Min Act: -0.0002

Data Index: 373599 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0715. Min Act: -0.0002

Data Index: 570699 (C4 (Web Text))

Max Activating Token Index: 997