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

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

Neuron 2222 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.9817. Min Act: -0.0001

Data Index: 1015093 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.8865. Min Act: -0.0001

Data Index: 805004 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.7797. Min Act: -0.0001

Data Index: 268553 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.7311. Min Act: -0.0001

Data Index: 106349 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.6829. Min Act: -0.0001

Data Index: 617806 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.6388. Min Act: -0.0001

Data Index: 978885 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.6614. Min Act: -0.0001

Data Index: 587848 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.6411. Min Act: -0.0001

Data Index: 927719 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.6140. Min Act: -0.0001

Data Index: 763742 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.6060. Min Act: -0.0000

Data Index: 61835 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.6042. Min Act: -0.0001

Data Index: 1304082 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.5478. Min Act: -0.0001

Data Index: 105795 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.5957. Min Act: -0.0000

Data Index: 602986 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.5604. Min Act: -0.0001

Data Index: 1344 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.5523. Min Act: -0.0000

Data Index: 218851 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.5257. Min Act: -0.0001

Data Index: 433447 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.5457. Min Act: -0.0001

Data Index: 591517 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.5702. Min Act: -0.0001

Data Index: 1049400 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.5500. Min Act: -0.0001

Data Index: 214487 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.9817. Min Range: -0.9817

Max Act: 0.5112. Min Act: -0.0001

Data Index: 247765 (C4 (Web Text))

Max Activating Token Index: 94