Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2580 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5137. Min Range: -2.5137

Max Act: 2.5137. Min Act: -0.0000

Data Index: 1185146 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.8727. Min Act: -0.0000

Data Index: 1222404 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.7283. Min Act: -0.0000

Data Index: 42614 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.5974. Min Act: -0.0000

Data Index: 72886 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.6470. Min Act: -0.0000

Data Index: 439677 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.5619. Min Act: -0.0000

Data Index: 664948 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.5039. Min Act: -0.0000

Data Index: 618582 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.4580. Min Act: -0.0000

Data Index: 1199631 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.5394. Min Act: -0.0000

Data Index: 784471 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.5302. Min Act: -0.0000

Data Index: 1301370 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.5222. Min Act: -0.0000

Data Index: 903336 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.4892. Min Act: -0.0000

Data Index: 787750 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.4045. Min Act: -0.0000

Data Index: 680347 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.5591. Min Act: -0.0000

Data Index: 1347308 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.4632. Min Act: -0.0000

Data Index: 376083 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.3517. Min Act: -0.0000

Data Index: 311530 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.4297. Min Act: -0.0000

Data Index: 47925 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.4031. Min Act: -0.0000

Data Index: 452360 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.3931. Min Act: -0.0000

Data Index: 1100100 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 2.5137. Min Range: -2.5137

Max Act: 1.3896. Min Act: -0.0000

Data Index: 463491 (C4 (Web Text))

Max Activating Token Index: 422