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

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

Neuron 139 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1708. Min Act: -0.0000

Data Index: 944869 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1794. Min Act: -0.0001

Data Index: 788820 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1015501 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1523. Min Act: -0.0000

Data Index: 265402 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1592. Min Act: -0.0000

Data Index: 505654 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1339281 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1498. Min Act: -0.0000

Data Index: 70316 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1520. Min Act: -0.0000

Data Index: 1351045 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1529. Min Act: 0.0000

Data Index: 443397 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1512. Min Act: -0.0000

Data Index: 84151 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1519. Min Act: -0.0000

Data Index: 1068293 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1452. Min Act: -0.0000

Data Index: 819470 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1490. Min Act: -0.0001

Data Index: 220121 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1027976 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1400. Min Act: -0.0000

Data Index: 220783 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1276. Min Act: -0.0000

Data Index: 1087087 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1336. Min Act: -0.0000

Data Index: 100925 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1351. Min Act: -0.0001

Data Index: 579236 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1342. Min Act: -0.0000

Data Index: 652133 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.1794. Min Range: -0.1794

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1190829 (C4 (Web Text))

Max Activating Token Index: 484