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

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

Neuron 3170 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1512003 (Python Code)

Max Activating Token Index: 37

Text #1

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1276863 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0964. Min Act: -0.0000

Data Index: 784523 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0917. Min Act: -0.0000

Data Index: 492839 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0884. Min Act: -0.0000

Data Index: 172884 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0831. Min Act: -0.0000

Data Index: 1574911 (Python Code)

Max Activating Token Index: 767

Text #6

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1058761 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0819. Min Act: -0.0000

Data Index: 1181527 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0874. Min Act: -0.0000

Data Index: 1511447 (Python Code)

Max Activating Token Index: 997

Text #9

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0841. Min Act: -0.0000

Data Index: 1203972 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0799. Min Act: -0.0000

Data Index: 573689 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1195566 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0796. Min Act: -0.0000

Data Index: 518821 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0849. Min Act: -0.0001

Data Index: 177716 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0810. Min Act: -0.0000

Data Index: 179203 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0789. Min Act: -0.0000

Data Index: 447656 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0807. Min Act: -0.0000

Data Index: 924538 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0754. Min Act: -0.0000

Data Index: 1601388 (Python Code)

Max Activating Token Index: 763

Text #18

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0774. Min Act: -0.0000

Data Index: 1012913 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.1036. Min Range: -0.1036

Max Act: 0.0773. Min Act: -0.0000

Data Index: 87162 (C4 (Web Text))

Max Activating Token Index: 567