Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 170 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 1.1024. Min Range: -1.1024

Max Act: 1.1024. Min Act: -0.0001

Data Index: 888767 (The Pile)

Max Activating Token Index: 280

Text #1

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.9033. Min Act: -0.0001

Data Index: 1114048 (The Pile)

Max Activating Token Index: 426

Text #2

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7698. Min Act: -0.0001

Data Index: 1438428 (The Pile)

Max Activating Token Index: 726

Text #3

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.8262. Min Act: -0.0001

Data Index: 123030 (The Pile)

Max Activating Token Index: 897

Text #4

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7247. Min Act: -0.0000

Data Index: 534978 (The Pile)

Max Activating Token Index: 650

Text #5

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7454. Min Act: -0.0001

Data Index: 794888 (The Pile)

Max Activating Token Index: 478

Text #6

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.6890. Min Act: -0.0001

Data Index: 993103 (The Pile)

Max Activating Token Index: 876

Text #7

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1771439 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1042132 (The Pile)

Max Activating Token Index: 125

Text #9

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.6838. Min Act: -0.0001

Data Index: 1562147 (The Pile)

Max Activating Token Index: 214

Text #10

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.6802. Min Act: -0.0001

Data Index: 628716 (The Pile)

Max Activating Token Index: 519

Text #11

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.6732. Min Act: -0.0000

Data Index: 1593801 (The Pile)

Max Activating Token Index: 476

Text #12

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.6357. Min Act: -0.0001

Data Index: 1946307 (The Pile)

Max Activating Token Index: 127

Text #13

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.6475. Min Act: -0.0001

Data Index: 1412230 (The Pile)

Max Activating Token Index: 247

Text #14

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.6348. Min Act: -0.0001

Data Index: 1698359 (The Pile)

Max Activating Token Index: 415

Text #15

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.5483. Min Act: -0.0000

Data Index: 578063 (The Pile)

Max Activating Token Index: 793

Text #16

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.6231. Min Act: -0.0001

Data Index: 999670 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.5585. Min Act: -0.0001

Data Index: 1595906 (The Pile)

Max Activating Token Index: 848

Text #18

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.5790. Min Act: -0.0000

Data Index: 1878417 (The Pile)

Max Activating Token Index: 225

Text #19

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.5934. Min Act: -0.0001

Data Index: 628353 (The Pile)

Max Activating Token Index: 60