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

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

Neuron 735 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5888. Min Range: -3.5888

Max Act: 3.5857. Min Act: -0.0000

Data Index: 803494 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 3.5888. Min Range: -3.5888

Max Act: 3.5888. Min Act: -0.0000

Data Index: 250709 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 3.5888. Min Range: -3.5888

Max Act: 3.2198. Min Act: -0.0000

Data Index: 824714 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 3.5888. Min Range: -3.5888

Max Act: 2.8812. Min Act: -0.0000

Data Index: 292911 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 3.5888. Min Range: -3.5888

Max Act: 3.2681. Min Act: -0.0000

Data Index: 520277 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 3.5888. Min Range: -3.5888

Max Act: 2.8007. Min Act: -0.0000

Data Index: 971420 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 3.5888. Min Range: -3.5888

Max Act: 3.0258. Min Act: -0.0000

Data Index: 871076 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 3.5888. Min Range: -3.5888

Max Act: 2.7540. Min Act: -0.0000

Data Index: 1193792 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.5888. Min Range: -3.5888

Max Act: 2.8626. Min Act: -0.0000

Data Index: 842752 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 3.5888. Min Range: -3.5888

Max Act: 2.6772. Min Act: -0.0000

Data Index: 243237 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 3.5888. Min Range: -3.5888

Max Act: 2.3645. Min Act: -0.0000

Data Index: 1310904 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 3.5888. Min Range: -3.5888

Max Act: 2.0858. Min Act: -0.0000

Data Index: 830643 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 3.5888. Min Range: -3.5888

Max Act: 1.6350. Min Act: -0.0000

Data Index: 886059 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 3.5888. Min Range: -3.5888

Max Act: 1.5016. Min Act: -0.0000

Data Index: 878964 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 3.5888. Min Range: -3.5888

Max Act: 1.3226. Min Act: -0.0000

Data Index: 886821 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 3.5888. Min Range: -3.5888

Max Act: 1.2842. Min Act: -0.0000

Data Index: 717905 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 3.5888. Min Range: -3.5888

Max Act: 1.2007. Min Act: -0.0000

Data Index: 1145985 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 3.5888. Min Range: -3.5888

Max Act: 1.0887. Min Act: -0.0000

Data Index: 959801 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 3.5888. Min Range: -3.5888

Max Act: 1.0813. Min Act: -0.0000

Data Index: 84448 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 3.5888. Min Range: -3.5888

Max Act: 1.0130. Min Act: -0.0000

Data Index: 710745 (C4 (Web Text))

Max Activating Token Index: 17