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

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

Neuron 4495 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0531. Min Range: -2.0531

Max Act: 2.0531. Min Act: -0.0000

Data Index: 9129 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 2.0531. Min Range: -2.0531

Max Act: 1.1801. Min Act: -0.0000

Data Index: 518042 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 2.0531. Min Range: -2.0531

Max Act: 1.2436. Min Act: -0.0000

Data Index: 468762 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 2.0531. Min Range: -2.0531

Max Act: 0.9658. Min Act: -0.0000

Data Index: 1194685 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 2.0531. Min Range: -2.0531

Max Act: 0.9394. Min Act: -0.0000

Data Index: 1234955 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 2.0531. Min Range: -2.0531

Max Act: 1.1035. Min Act: -0.0000

Data Index: 632086 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 2.0531. Min Range: -2.0531

Max Act: 0.9663. Min Act: -0.0000

Data Index: 1091461 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 2.0531. Min Range: -2.0531

Max Act: 1.0074. Min Act: -0.0000

Data Index: 808790 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 2.0531. Min Range: -2.0531

Max Act: 0.8851. Min Act: -0.0000

Data Index: 208580 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 2.0531. Min Range: -2.0531

Max Act: 0.8254. Min Act: -0.0000

Data Index: 1197889 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 2.0531. Min Range: -2.0531

Max Act: 0.8325. Min Act: -0.0000

Data Index: 446016 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 2.0531. Min Range: -2.0531

Max Act: 0.8064. Min Act: -0.0000

Data Index: 1098846 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 2.0531. Min Range: -2.0531

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1242969 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 2.0531. Min Range: -2.0531

Max Act: 0.7511. Min Act: -0.0000

Data Index: 1099390 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 2.0531. Min Range: -2.0531

Max Act: 0.8015. Min Act: -0.0000

Data Index: 398780 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 2.0531. Min Range: -2.0531

Max Act: 0.7945. Min Act: -0.0000

Data Index: 537010 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 2.0531. Min Range: -2.0531

Max Act: 0.7188. Min Act: -0.0000

Data Index: 793501 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 2.0531. Min Range: -2.0531

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1006715 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 2.0531. Min Range: -2.0531

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1099989 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 2.0531. Min Range: -2.0531

Max Act: 0.6928. Min Act: -0.0000

Data Index: 548244 (C4 (Web Text))

Max Activating Token Index: 773