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

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

Neuron 1479 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2097. Min Range: -1.2097

Max Act: 1.2097. Min Act: -0.0001

Data Index: 170651 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 1.2097. Min Range: -1.2097

Max Act: 1.0698. Min Act: -0.0001

Data Index: 1302427 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.9723. Min Act: -0.0001

Data Index: 810389 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.7939. Min Act: -0.0001

Data Index: 501989 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.6708. Min Act: -0.0001

Data Index: 1112187 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.7354. Min Act: -0.0001

Data Index: 587673 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.8119. Min Act: -0.0001

Data Index: 361556 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.7466. Min Act: -0.0001

Data Index: 97676 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.6865. Min Act: -0.0001

Data Index: 84491 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.7391. Min Act: -0.0001

Data Index: 14228 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.6789. Min Act: -0.0001

Data Index: 896130 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.6337. Min Act: -0.0001

Data Index: 4615 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.6619. Min Act: -0.0001

Data Index: 578207 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.6947. Min Act: -0.0001

Data Index: 876962 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.6729. Min Act: -0.0001

Data Index: 1236425 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.6810. Min Act: -0.0001

Data Index: 1030556 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.7536. Min Act: -0.0001

Data Index: 626012 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.6486. Min Act: -0.0001

Data Index: 118741 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.6422. Min Act: -0.0001

Data Index: 6891 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 1.2097. Min Range: -1.2097

Max Act: 0.6409. Min Act: -0.0001

Data Index: 261721 (C4 (Web Text))

Max Activating Token Index: 703