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

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

Neuron 4867 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: 3.0006. Min Range: -3.0006

Max Act: 3.0006. Min Act: -0.0000

Data Index: 1032672 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.3749. Min Act: -0.0000

Data Index: 900188 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.4271. Min Act: -0.0000

Data Index: 373092 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.2862. Min Act: -0.0000

Data Index: 252109 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.1873. Min Act: -0.0000

Data Index: 132537 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.1641. Min Act: -0.0000

Data Index: 661876 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.1018. Min Act: -0.0000

Data Index: 410905 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.1373. Min Act: -0.0000

Data Index: 1410533 (Python Code)

Max Activating Token Index: 782

Text #8

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.1304. Min Act: -0.0000

Data Index: 702158 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 3.0006. Min Range: -3.0006

Max Act: 1.8518. Min Act: -0.0000

Data Index: 900756 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.1382. Min Act: -0.0000

Data Index: 1530768 (Python Code)

Max Activating Token Index: 712

Text #11

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.0128. Min Act: -0.0000

Data Index: 1362329 (Python Code)

Max Activating Token Index: 627

Text #12

Max Range: 3.0006. Min Range: -3.0006

Max Act: 1.9984. Min Act: -0.0000

Data Index: 1364061 (Python Code)

Max Activating Token Index: 723

Text #13

Max Range: 3.0006. Min Range: -3.0006

Max Act: 1.9855. Min Act: -0.0000

Data Index: 592951 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.0759. Min Act: -0.0000

Data Index: 1416919 (Python Code)

Max Activating Token Index: 294

Text #15

Max Range: 3.0006. Min Range: -3.0006

Max Act: 2.0079. Min Act: -0.0000

Data Index: 1588177 (Python Code)

Max Activating Token Index: 760

Text #16

Max Range: 3.0006. Min Range: -3.0006

Max Act: 1.7913. Min Act: -0.0000

Data Index: 1548929 (Python Code)

Max Activating Token Index: 32

Text #17

Max Range: 3.0006. Min Range: -3.0006

Max Act: 1.8868. Min Act: -0.0000

Data Index: 41328 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 3.0006. Min Range: -3.0006

Max Act: 1.8770. Min Act: -0.0000

Data Index: 953593 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 3.0006. Min Range: -3.0006

Max Act: 1.7685. Min Act: -0.0000

Data Index: 969429 (C4 (Web Text))

Max Activating Token Index: 418