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

Dataset: The Pile

Neuron 4387 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: 0.8016. Min Range: -0.8016

Max Act: 0.8016. Min Act: -0.0000

Data Index: 1003006 (The Pile)

Max Activating Token Index: 985

Text #1

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6720. Min Act: -0.0000

Data Index: 227457 (The Pile)

Max Activating Token Index: 874

Text #2

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1491558 (The Pile)

Max Activating Token Index: 894

Text #3

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1630197 (The Pile)

Max Activating Token Index: 524

Text #4

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.4300. Min Act: -0.0000

Data Index: 1151119 (The Pile)

Max Activating Token Index: 861

Text #5

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1125982 (The Pile)

Max Activating Token Index: 274

Text #6

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1616227 (The Pile)

Max Activating Token Index: 534

Text #7

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1240623 (The Pile)

Max Activating Token Index: 900

Text #8

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1480488 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.3917. Min Act: -0.0000

Data Index: 1192906 (The Pile)

Max Activating Token Index: 832

Text #10

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.4394. Min Act: -0.0000

Data Index: 48757 (The Pile)

Max Activating Token Index: 414

Text #11

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1592882 (The Pile)

Max Activating Token Index: 679

Text #12

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1518759 (The Pile)

Max Activating Token Index: 443

Text #13

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.4107. Min Act: -0.0000

Data Index: 488305 (The Pile)

Max Activating Token Index: 378

Text #14

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.4042. Min Act: -0.0000

Data Index: 122465 (The Pile)

Max Activating Token Index: 497

Text #15

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.3711. Min Act: -0.0000

Data Index: 251160 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.3820. Min Act: -0.0000

Data Index: 1616854 (The Pile)

Max Activating Token Index: 178

Text #17

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1027893 (The Pile)

Max Activating Token Index: 523

Text #18

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.3904. Min Act: -0.0000

Data Index: 809783 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.3980. Min Act: -0.0000

Data Index: 635421 (The Pile)

Max Activating Token Index: 724