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

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

Neuron 1933 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.9372. Min Act: -0.0001

Data Index: 130881 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.9377. Min Act: -0.0001

Data Index: 874099 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.8689. Min Act: -0.0001

Data Index: 1199256 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.8390. Min Act: -0.0001

Data Index: 1008653 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7967. Min Act: -0.0001

Data Index: 501698 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.8028. Min Act: -0.0001

Data Index: 897172 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7751. Min Act: -0.0001

Data Index: 922036 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7443. Min Act: -0.0001

Data Index: 677707 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7762. Min Act: -0.0001

Data Index: 800415 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7757. Min Act: -0.0001

Data Index: 640029 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7745. Min Act: -0.0001

Data Index: 289722 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7667. Min Act: -0.0001

Data Index: 208340 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7391. Min Act: -0.0001

Data Index: 1055052 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7341. Min Act: -0.0001

Data Index: 148426 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7562. Min Act: -0.0001

Data Index: 202000 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7564. Min Act: -0.0001

Data Index: 351829 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7476. Min Act: -0.0001

Data Index: 67528 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7632. Min Act: -0.0001

Data Index: 673396 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7132. Min Act: -0.0001

Data Index: 302073 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7023. Min Act: -0.0001

Data Index: 837479 (C4 (Web Text))

Max Activating Token Index: 631