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

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

Neuron 3473 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0966. Min Act: -0.0002

Data Index: 279283 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1229651 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0916. Min Act: -0.0002

Data Index: 584008 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0913. Min Act: -0.0002

Data Index: 1267051 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0894. Min Act: -0.0002

Data Index: 668274 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0905. Min Act: -0.0002

Data Index: 1327838 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1020664 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0822. Min Act: -0.0002

Data Index: 275454 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0749. Min Act: -0.0002

Data Index: 240467 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1389344 (Python Code)

Max Activating Token Index: 445

Text #10

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0741. Min Act: -0.0002

Data Index: 35140 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0773. Min Act: -0.0002

Data Index: 848796 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1280096 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0760. Min Act: -0.0002

Data Index: 691176 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0710. Min Act: -0.0002

Data Index: 247374 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0690. Min Act: -0.0002

Data Index: 729378 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0710. Min Act: -0.0002

Data Index: 908023 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0686. Min Act: -0.0002

Data Index: 748053 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1229948 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0680. Min Act: -0.0002

Data Index: 46491 (C4 (Web Text))

Max Activating Token Index: 862