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

Dataset: The Pile

Neuron 3869 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8762. Min Act: -0.0000

Data Index: 296707 (The Pile)

Max Activating Token Index: 180

Text #1

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.9552. Min Act: -0.0000

Data Index: 199366 (The Pile)

Max Activating Token Index: 886

Text #2

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8157. Min Act: -0.0000

Data Index: 1823845 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7555. Min Act: -0.0000

Data Index: 50068 (The Pile)

Max Activating Token Index: 326

Text #4

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7711. Min Act: -0.0000

Data Index: 687594 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7435. Min Act: -0.0000

Data Index: 1659714 (The Pile)

Max Activating Token Index: 219

Text #6

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7684. Min Act: -0.0000

Data Index: 704150 (The Pile)

Max Activating Token Index: 219

Text #7

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7547. Min Act: -0.0000

Data Index: 7272 (The Pile)

Max Activating Token Index: 951

Text #8

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7299. Min Act: -0.0000

Data Index: 669736 (The Pile)

Max Activating Token Index: 799

Text #9

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7250. Min Act: -0.0000

Data Index: 1896008 (The Pile)

Max Activating Token Index: 181

Text #10

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7100. Min Act: -0.0000

Data Index: 532317 (The Pile)

Max Activating Token Index: 104

Text #11

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1464475 (The Pile)

Max Activating Token Index: 460

Text #12

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1318025 (The Pile)

Max Activating Token Index: 307

Text #13

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6696. Min Act: -0.0000

Data Index: 434822 (The Pile)

Max Activating Token Index: 493

Text #14

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6817. Min Act: -0.0000

Data Index: 234474 (The Pile)

Max Activating Token Index: 217

Text #15

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6631. Min Act: -0.0000

Data Index: 766099 (The Pile)

Max Activating Token Index: 678

Text #16

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1695673 (The Pile)

Max Activating Token Index: 731

Text #17

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1511549 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.5933. Min Act: -0.0000

Data Index: 18884 (The Pile)

Max Activating Token Index: 111

Text #19

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6114. Min Act: -0.0000

Data Index: 896130 (The Pile)

Max Activating Token Index: 674