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

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

Neuron 1426 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.1624. Min Act: -0.0000

Data Index: 104640 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1015372 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9614. Min Act: -0.0000

Data Index: 524305 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8878. Min Act: -0.0000

Data Index: 1029869 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9410. Min Act: -0.0000

Data Index: 376743 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8966. Min Act: -0.0000

Data Index: 38438 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8220. Min Act: -0.0000

Data Index: 1200345 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.9068. Min Act: -0.0000

Data Index: 246049 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8652. Min Act: -0.0000

Data Index: 602883 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8273. Min Act: -0.0000

Data Index: 1056229 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8494. Min Act: -0.0000

Data Index: 82806 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8475. Min Act: -0.0000

Data Index: 964184 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8093. Min Act: -0.0000

Data Index: 1233757 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.8422. Min Act: -0.0000

Data Index: 1527002 (Python Code)

Max Activating Token Index: 99

Text #14

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1180138 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.7772. Min Act: -0.0000

Data Index: 952794 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.7973. Min Act: -0.0000

Data Index: 218705 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.7908. Min Act: -0.0000

Data Index: 1000460 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.7888. Min Act: -0.0000

Data Index: 253145 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 1.1624. Min Range: -1.1624

Max Act: 0.7749. Min Act: -0.0000

Data Index: 1171833 (C4 (Web Text))

Max Activating Token Index: 260