Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2974 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.9620. Min Act: -0.0001

Data Index: 4712 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.8541. Min Act: -0.0001

Data Index: 533926 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.7709. Min Act: -0.0001

Data Index: 557681 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.7057. Min Act: -0.0001

Data Index: 855503 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.6976. Min Act: -0.0000

Data Index: 182160 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.7548. Min Act: -0.0000

Data Index: 634066 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.7414. Min Act: -0.0001

Data Index: 800928 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.7375. Min Act: -0.0000

Data Index: 332468 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.6821. Min Act: -0.0000

Data Index: 619613 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.6806. Min Act: -0.0001

Data Index: 1126654 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.7007. Min Act: -0.0001

Data Index: 29074 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.6789. Min Act: -0.0001

Data Index: 723330 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.6710. Min Act: -0.0001

Data Index: 269275 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.6724. Min Act: -0.0001

Data Index: 417999 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.6620. Min Act: -0.0001

Data Index: 1244572 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1314056 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1204104 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.6576. Min Act: -0.0001

Data Index: 96513 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.6591. Min Act: -0.0001

Data Index: 218729 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.9620. Min Range: -0.9620

Max Act: 0.6109. Min Act: -0.0000

Data Index: 468639 (C4 (Web Text))

Max Activating Token Index: 496