Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 715 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.4451. Min Act: -0.0005

Data Index: 646084 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.4169. Min Act: -0.0005

Data Index: 680913 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.4085. Min Act: -0.0005

Data Index: 1116887 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3557. Min Act: -0.0005

Data Index: 548871 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3793. Min Act: -0.0005

Data Index: 1003768 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3779. Min Act: -0.0005

Data Index: 1110288 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.4033. Min Act: -0.0005

Data Index: 1095485 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3882. Min Act: -0.0005

Data Index: 1265852 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3424. Min Act: -0.0005

Data Index: 458265 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3429. Min Act: -0.0005

Data Index: 191860 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3510. Min Act: -0.0005

Data Index: 941712 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3585. Min Act: -0.0005

Data Index: 469913 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3576. Min Act: -0.0005

Data Index: 1170042 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3368. Min Act: -0.0005

Data Index: 356854 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3583. Min Act: -0.0005

Data Index: 768514 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3581. Min Act: -0.0005

Data Index: 1077309 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3564. Min Act: -0.0005

Data Index: 96915 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3411. Min Act: -0.0005

Data Index: 99718 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3272. Min Act: -0.0005

Data Index: 503327 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.4451. Min Range: -0.4451

Max Act: 0.3465. Min Act: -0.0005

Data Index: 1006852 (C4 (Web Text))

Max Activating Token Index: 129