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

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

Neuron 1804 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.7626. Min Act: -0.0000

Data Index: 325651 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.7376. Min Act: -0.0000

Data Index: 317253 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6995. Min Act: -0.0000

Data Index: 648679 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.6932. Min Act: -0.0000

Data Index: 413755 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1265000 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5893. Min Act: -0.0000

Data Index: 853341 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5642. Min Act: -0.0000

Data Index: 778402 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5492. Min Act: -0.0000

Data Index: 946353 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1046079 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5750. Min Act: -0.0000

Data Index: 694877 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5727. Min Act: -0.0000

Data Index: 270790 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5699. Min Act: -0.0000

Data Index: 541970 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5888. Min Act: -0.0000

Data Index: 100211 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1200869 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1258958 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5348. Min Act: -0.0000

Data Index: 975475 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5387. Min Act: -0.0000

Data Index: 61601 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5651. Min Act: -0.0000

Data Index: 369048 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5439. Min Act: -0.0000

Data Index: 316272 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.7626. Min Range: -0.7626

Max Act: 0.5388. Min Act: -0.0000

Data Index: 56849 (C4 (Web Text))

Max Activating Token Index: 911