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

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

Neuron 4423 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: 0.0936. Min Range: -0.0936

Max Act: 0.0936. Min Act: -0.0002

Data Index: 845538 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0837. Min Act: -0.0002

Data Index: 96234 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1101581 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0816. Min Act: -0.0002

Data Index: 812318 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1296487 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0772. Min Act: -0.0002

Data Index: 320934 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0792. Min Act: -0.0002

Data Index: 368456 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0768. Min Act: -0.0002

Data Index: 457895 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0754. Min Act: -0.0002

Data Index: 399054 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0753. Min Act: -0.0002

Data Index: 397500 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0721. Min Act: -0.0002

Data Index: 249981 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0733. Min Act: -0.0002

Data Index: 475426 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0735. Min Act: -0.0002

Data Index: 630866 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0713. Min Act: -0.0002

Data Index: 1137384 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0728. Min Act: -0.0002

Data Index: 633243 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0683. Min Act: -0.0002

Data Index: 363498 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1188500 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0724. Min Act: -0.0002

Data Index: 1159706 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1079926 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1154468 (C4 (Web Text))

Max Activating Token Index: 868