Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2665 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7618. Min Act: -0.0000

Data Index: 928450 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6599. Min Act: -0.0000

Data Index: 413497 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6763. Min Act: -0.0000

Data Index: 128674 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6096. Min Act: -0.0000

Data Index: 48038 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6229. Min Act: -0.0000

Data Index: 555363 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6483. Min Act: -0.0000

Data Index: 220229 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6156. Min Act: -0.0000

Data Index: 444702 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1003533 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6564. Min Act: -0.0000

Data Index: 367150 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.5980. Min Act: -0.0000

Data Index: 98191 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.5999. Min Act: -0.0000

Data Index: 392940 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6194. Min Act: -0.0000

Data Index: 514263 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6613. Min Act: -0.0000

Data Index: 160172 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.5924. Min Act: -0.0000

Data Index: 231956 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6291. Min Act: -0.0000

Data Index: 200817 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6675. Min Act: -0.0000

Data Index: 491859 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1329843 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6240. Min Act: -0.0000

Data Index: 1087351 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6190. Min Act: -0.0000

Data Index: 562382 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6116. Min Act: -0.0000

Data Index: 253901 (C4 (Web Text))

Max Activating Token Index: 628