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

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

Neuron 4925 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1082156 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1139988 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.5199. Min Act: -0.0000

Data Index: 988837 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.5304. Min Act: -0.0000

Data Index: 60935 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1257893 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.5162. Min Act: -0.0000

Data Index: 453722 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4396. Min Act: -0.0000

Data Index: 505757 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1321852 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4938. Min Act: -0.0000

Data Index: 966768 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4588. Min Act: -0.0000

Data Index: 986899 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4756. Min Act: -0.0000

Data Index: 611097 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4125. Min Act: -0.0000

Data Index: 464530 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4111. Min Act: -0.0000

Data Index: 404167 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1220112 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.3820. Min Act: -0.0000

Data Index: 279486 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4167. Min Act: -0.0000

Data Index: 508456 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.3892. Min Act: -0.0000

Data Index: 32225 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.3879. Min Act: -0.0000

Data Index: 1352624 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.3900. Min Act: -0.0000

Data Index: 1124635 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.5738. Min Range: -0.5738

Max Act: 0.4027. Min Act: -0.0000

Data Index: 209733 (C4 (Web Text))

Max Activating Token Index: 726