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

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

Neuron 257 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.6247. Min Act: -0.0000

Data Index: 664440 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 4.6247. Min Range: -4.6247

Max Act: 4.0778. Min Act: -0.0000

Data Index: 106067 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 4.6247. Min Range: -4.6247

Max Act: 3.6352. Min Act: -0.0000

Data Index: 171339 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 4.6247. Min Range: -4.6247

Max Act: 3.6523. Min Act: -0.0000

Data Index: 764482 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 4.6247. Min Range: -4.6247

Max Act: 3.3796. Min Act: -0.0000

Data Index: 175139 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 4.6247. Min Range: -4.6247

Max Act: 3.5836. Min Act: -0.0000

Data Index: 684331 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 4.6247. Min Range: -4.6247

Max Act: 3.3648. Min Act: -0.0000

Data Index: 1005953 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 4.6247. Min Range: -4.6247

Max Act: 3.1645. Min Act: -0.0000

Data Index: 1067860 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 4.6247. Min Range: -4.6247

Max Act: 3.5958. Min Act: -0.0000

Data Index: 501956 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 4.6247. Min Range: -4.6247

Max Act: 3.2017. Min Act: -0.0000

Data Index: 645345 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 4.6247. Min Range: -4.6247

Max Act: 3.2279. Min Act: -0.0000

Data Index: 496909 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 4.6247. Min Range: -4.6247

Max Act: 2.8545. Min Act: -0.0000

Data Index: 606860 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 4.6247. Min Range: -4.6247

Max Act: 3.3116. Min Act: -0.0000

Data Index: 505536 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 4.6247. Min Range: -4.6247

Max Act: 3.1673. Min Act: -0.0000

Data Index: 857790 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 4.6247. Min Range: -4.6247

Max Act: 3.0311. Min Act: -0.0000

Data Index: 1212237 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 4.6247. Min Range: -4.6247

Max Act: 3.1425. Min Act: -0.0000

Data Index: 1119819 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 4.6247. Min Range: -4.6247

Max Act: 2.7089. Min Act: -0.0000

Data Index: 1087164 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 4.6247. Min Range: -4.6247

Max Act: 2.9649. Min Act: -0.0000

Data Index: 1014117 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 4.6247. Min Range: -4.6247

Max Act: 2.9753. Min Act: -0.0000

Data Index: 55681 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 4.6247. Min Range: -4.6247

Max Act: 3.1537. Min Act: -0.0000

Data Index: 1148134 (C4 (Web Text))

Max Activating Token Index: 219