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

Dataset: The Pile

Neuron 1851 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4473. Min Range: -7.4473

Max Act: 7.2832. Min Act: -0.0000

Data Index: 1887152 (The Pile)

Max Activating Token Index: 270

Text #1

Max Range: 7.4473. Min Range: -7.4473

Max Act: 7.4473. Min Act: -0.0000

Data Index: 1461622 (The Pile)

Max Activating Token Index: 340

Text #2

Max Range: 7.4473. Min Range: -7.4473

Max Act: 6.9695. Min Act: -0.0000

Data Index: 740171 (The Pile)

Max Activating Token Index: 419

Text #3

Max Range: 7.4473. Min Range: -7.4473

Max Act: 6.9393. Min Act: -0.0000

Data Index: 1961258 (The Pile)

Max Activating Token Index: 516

Text #4

Max Range: 7.4473. Min Range: -7.4473

Max Act: 6.3855. Min Act: -0.0000

Data Index: 787373 (The Pile)

Max Activating Token Index: 481

Text #5

Max Range: 7.4473. Min Range: -7.4473

Max Act: 6.7880. Min Act: -0.0000

Data Index: 766754 (The Pile)

Max Activating Token Index: 118

Text #6

Max Range: 7.4473. Min Range: -7.4473

Max Act: 6.7371. Min Act: -0.0000

Data Index: 1103001 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 7.4473. Min Range: -7.4473

Max Act: 6.6317. Min Act: -0.0000

Data Index: 419209 (The Pile)

Max Activating Token Index: 712

Text #8

Max Range: 7.4473. Min Range: -7.4473

Max Act: 6.8495. Min Act: -0.0000

Data Index: 1234212 (The Pile)

Max Activating Token Index: 623

Text #9

Max Range: 7.4473. Min Range: -7.4473

Max Act: 6.3681. Min Act: -0.0000

Data Index: 932270 (The Pile)

Max Activating Token Index: 62

Text #10

Max Range: 7.4473. Min Range: -7.4473

Max Act: 5.7398. Min Act: -0.0000

Data Index: 771788 (The Pile)

Max Activating Token Index: 236

Text #11

Max Range: 7.4473. Min Range: -7.4473

Max Act: 5.8008. Min Act: -0.0000

Data Index: 1002156 (The Pile)

Max Activating Token Index: 527

Text #12

Max Range: 7.4473. Min Range: -7.4473

Max Act: 5.7799. Min Act: -0.0000

Data Index: 622501 (The Pile)

Max Activating Token Index: 349

Text #13

Max Range: 7.4473. Min Range: -7.4473

Max Act: 5.1183. Min Act: -0.0000

Data Index: 1317939 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 7.4473. Min Range: -7.4473

Max Act: 5.4022. Min Act: -0.0000

Data Index: 629454 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 7.4473. Min Range: -7.4473

Max Act: 5.1642. Min Act: -0.0000

Data Index: 1368370 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 7.4473. Min Range: -7.4473

Max Act: 4.3765. Min Act: -0.0000

Data Index: 1883851 (The Pile)

Max Activating Token Index: 221

Text #17

Max Range: 7.4473. Min Range: -7.4473

Max Act: 4.1706. Min Act: -0.0000

Data Index: 1998365 (The Pile)

Max Activating Token Index: 58

Text #18

Max Range: 7.4473. Min Range: -7.4473

Max Act: 5.0024. Min Act: -0.0000

Data Index: 153571 (The Pile)

Max Activating Token Index: 114

Text #19

Max Range: 7.4473. Min Range: -7.4473

Max Act: 4.5707. Min Act: -0.0000

Data Index: 461910 (The Pile)

Max Activating Token Index: 126