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

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

Neuron 2889 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2604. Min Range: -2.2604

Max Act: 2.2604. Min Act: -0.0000

Data Index: 27050 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 2.2604. Min Range: -2.2604

Max Act: 2.1577. Min Act: -0.0000

Data Index: 195061 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 2.2604. Min Range: -2.2604

Max Act: 2.2141. Min Act: -0.0000

Data Index: 1169198 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 2.2604. Min Range: -2.2604

Max Act: 2.0669. Min Act: -0.0000

Data Index: 771507 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 2.2604. Min Range: -2.2604

Max Act: 2.1500. Min Act: -0.0000

Data Index: 284108 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 2.2604. Min Range: -2.2604

Max Act: 2.0998. Min Act: -0.0000

Data Index: 216899 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 2.2604. Min Range: -2.2604

Max Act: 1.6654. Min Act: -0.0000

Data Index: 658089 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 2.2604. Min Range: -2.2604

Max Act: 1.7506. Min Act: -0.0000

Data Index: 253556 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 2.2604. Min Range: -2.2604

Max Act: 1.5822. Min Act: -0.0000

Data Index: 1182235 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 2.2604. Min Range: -2.2604

Max Act: 1.5747. Min Act: -0.0000

Data Index: 1074765 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 2.2604. Min Range: -2.2604

Max Act: 1.4100. Min Act: -0.0000

Data Index: 1232386 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 2.2604. Min Range: -2.2604

Max Act: 1.4441. Min Act: -0.0000

Data Index: 927909 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 2.2604. Min Range: -2.2604

Max Act: 1.4377. Min Act: -0.0000

Data Index: 393912 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 2.2604. Min Range: -2.2604

Max Act: 1.2401. Min Act: -0.0000

Data Index: 888881 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 2.2604. Min Range: -2.2604

Max Act: 1.3456. Min Act: -0.0000

Data Index: 437921 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 2.2604. Min Range: -2.2604

Max Act: 1.3815. Min Act: -0.0000

Data Index: 999833 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 2.2604. Min Range: -2.2604

Max Act: 1.3494. Min Act: -0.0000

Data Index: 1057747 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 2.2604. Min Range: -2.2604

Max Act: 1.4660. Min Act: -0.0000

Data Index: 280985 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 2.2604. Min Range: -2.2604

Max Act: 1.3935. Min Act: -0.0000

Data Index: 532350 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 2.2604. Min Range: -2.2604

Max Act: 1.3340. Min Act: -0.0000

Data Index: 341960 (C4 (Web Text))

Max Activating Token Index: 243