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

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

Neuron 4578 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4121. Min Range: -1.4121

Max Act: 1.4121. Min Act: -0.0000

Data Index: 1106013 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 1.4121. Min Range: -1.4121

Max Act: 1.3100. Min Act: -0.0000

Data Index: 612229 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 1.4121. Min Range: -1.4121

Max Act: 1.2633. Min Act: -0.0000

Data Index: 511228 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 1.4121. Min Range: -1.4121

Max Act: 1.2686. Min Act: -0.0000

Data Index: 651467 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 1.4121. Min Range: -1.4121

Max Act: 1.2428. Min Act: -0.0000

Data Index: 1188721 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 1.4121. Min Range: -1.4121

Max Act: 0.9232. Min Act: -0.0000

Data Index: 666009 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 1.4121. Min Range: -1.4121

Max Act: 0.9385. Min Act: -0.0000

Data Index: 890037 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 1.4121. Min Range: -1.4121

Max Act: 0.9816. Min Act: -0.0000

Data Index: 1092671 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 1.4121. Min Range: -1.4121

Max Act: 1.1310. Min Act: -0.0000

Data Index: 523686 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 1.4121. Min Range: -1.4121

Max Act: 0.9702. Min Act: -0.0000

Data Index: 302183 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 1.4121. Min Range: -1.4121

Max Act: 0.8404. Min Act: -0.0000

Data Index: 706418 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 1.4121. Min Range: -1.4121

Max Act: 0.9058. Min Act: -0.0000

Data Index: 649370 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 1.4121. Min Range: -1.4121

Max Act: 0.7656. Min Act: -0.0000

Data Index: 764755 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 1.4121. Min Range: -1.4121

Max Act: 0.9850. Min Act: -0.0000

Data Index: 518487 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 1.4121. Min Range: -1.4121

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1068938 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 1.4121. Min Range: -1.4121

Max Act: 0.7264. Min Act: -0.0000

Data Index: 519371 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 1.4121. Min Range: -1.4121

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1254736 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 1.4121. Min Range: -1.4121

Max Act: 0.7675. Min Act: -0.0000

Data Index: 73709 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 1.4121. Min Range: -1.4121

Max Act: 0.6400. Min Act: -0.0000

Data Index: 634535 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 1.4121. Min Range: -1.4121

Max Act: 0.7025. Min Act: -0.0000

Data Index: 126277 (C4 (Web Text))

Max Activating Token Index: 739