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

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

Neuron 3012 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0341. Min Range: -1.0341

Max Act: 1.0341. Min Act: -0.0000

Data Index: 459413 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.9272. Min Act: -0.0000

Data Index: 408496 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.8929. Min Act: -0.0000

Data Index: 85685 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.8653. Min Act: -0.0000

Data Index: 882829 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.8737. Min Act: -0.0000

Data Index: 733379 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.8489. Min Act: -0.0000

Data Index: 1043179 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.8480. Min Act: -0.0000

Data Index: 376742 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7917. Min Act: -0.0000

Data Index: 540862 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.8638. Min Act: -0.0000

Data Index: 1154758 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.8220. Min Act: -0.0000

Data Index: 254551 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7948. Min Act: -0.0000

Data Index: 500214 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.8102. Min Act: -0.0000

Data Index: 230017 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.8048. Min Act: -0.0000

Data Index: 867834 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.8229. Min Act: -0.0000

Data Index: 914032 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7670. Min Act: -0.0000

Data Index: 238381 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7848. Min Act: -0.0000

Data Index: 1143948 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7797. Min Act: -0.0000

Data Index: 1347066 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1150813 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1288815 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 1.0341. Min Range: -1.0341

Max Act: 0.7911. Min Act: -0.0000

Data Index: 127457 (C4 (Web Text))

Max Activating Token Index: 742