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

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

Neuron 843 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9382. Min Range: -1.9382

Max Act: 1.9246. Min Act: -0.0000

Data Index: 593230 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 1.9382. Min Range: -1.9382

Max Act: 1.9382. Min Act: -0.0000

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 1.9382. Min Range: -1.9382

Max Act: 1.5995. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 1.9382. Min Range: -1.9382

Max Act: 1.4613. Min Act: -0.0000

Data Index: 289939 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 1.9382. Min Range: -1.9382

Max Act: 1.4284. Min Act: -0.0000

Data Index: 1029674 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 1.9382. Min Range: -1.9382

Max Act: 1.3619. Min Act: -0.0000

Data Index: 1488926 (Python Code)

Max Activating Token Index: 717

Text #6

Max Range: 1.9382. Min Range: -1.9382

Max Act: 1.2921. Min Act: -0.0000

Data Index: 1469821 (Python Code)

Max Activating Token Index: 790

Text #7

Max Range: 1.9382. Min Range: -1.9382

Max Act: 1.1318. Min Act: -0.0000

Data Index: 1597039 (Python Code)

Max Activating Token Index: 667

Text #8

Max Range: 1.9382. Min Range: -1.9382

Max Act: 1.0905. Min Act: -0.0000

Data Index: 1620057 (Python Code)

Max Activating Token Index: 749

Text #9

Max Range: 1.9382. Min Range: -1.9382

Max Act: 1.0794. Min Act: -0.0000

Data Index: 1555556 (Python Code)

Max Activating Token Index: 553

Text #10

Max Range: 1.9382. Min Range: -1.9382

Max Act: 1.0708. Min Act: -0.0000

Data Index: 1130140 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 1.9382. Min Range: -1.9382

Max Act: 1.0361. Min Act: -0.0000

Data Index: 1377527 (Python Code)

Max Activating Token Index: 935

Text #12

Max Range: 1.9382. Min Range: -1.9382

Max Act: 1.0185. Min Act: -0.0000

Data Index: 1403131 (Python Code)

Max Activating Token Index: 620

Text #13

Max Range: 1.9382. Min Range: -1.9382

Max Act: 0.9856. Min Act: -0.0000

Data Index: 1611632 (Python Code)

Max Activating Token Index: 597

Text #14

Max Range: 1.9382. Min Range: -1.9382

Max Act: 0.9432. Min Act: -0.0000

Data Index: 1090812 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 1.9382. Min Range: -1.9382

Max Act: 0.9536. Min Act: -0.0000

Data Index: 21887 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 1.9382. Min Range: -1.9382

Max Act: 0.9963. Min Act: -0.0000

Data Index: 125244 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 1.9382. Min Range: -1.9382

Max Act: 0.8697. Min Act: -0.0000

Data Index: 695819 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 1.9382. Min Range: -1.9382

Max Act: 0.9178. Min Act: -0.0000

Data Index: 924587 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 1.9382. Min Range: -1.9382

Max Act: 0.8063. Min Act: -0.0000

Data Index: 141576 (C4 (Web Text))

Max Activating Token Index: 168