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

Dataset: The Pile

Neuron 705 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1873824 (The Pile)

Max Activating Token Index: 127

Text #1

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1320339 (The Pile)

Max Activating Token Index: 473

Text #2

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3878. Min Act: -0.0000

Data Index: 1893705 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3860. Min Act: -0.0000

Data Index: 821475 (The Pile)

Max Activating Token Index: 231

Text #4

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1217747 (The Pile)

Max Activating Token Index: 292

Text #5

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3770. Min Act: -0.0000

Data Index: 364064 (The Pile)

Max Activating Token Index: 824

Text #6

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3429. Min Act: -0.0000

Data Index: 715289 (The Pile)

Max Activating Token Index: 543

Text #7

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3626. Min Act: -0.0000

Data Index: 197797 (The Pile)

Max Activating Token Index: 549

Text #8

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3551. Min Act: -0.0000

Data Index: 1086286 (The Pile)

Max Activating Token Index: 107

Text #9

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3542. Min Act: -0.0000

Data Index: 721931 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3598. Min Act: -0.0000

Data Index: 1979200 (The Pile)

Max Activating Token Index: 638

Text #11

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3432. Min Act: -0.0000

Data Index: 1726742 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3514. Min Act: -0.0000

Data Index: 141209 (The Pile)

Max Activating Token Index: 526

Text #13

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1942258 (The Pile)

Max Activating Token Index: 406

Text #14

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3756. Min Act: -0.0000

Data Index: 1698184 (The Pile)

Max Activating Token Index: 657

Text #15

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3610. Min Act: -0.0000

Data Index: 1936868 (The Pile)

Max Activating Token Index: 305

Text #16

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1042866 (The Pile)

Max Activating Token Index: 239

Text #17

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3224. Min Act: -0.0001

Data Index: 1033824 (The Pile)

Max Activating Token Index: 960

Text #18

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1169756 (The Pile)

Max Activating Token Index: 418

Text #19

Max Range: 0.4669. Min Range: -0.4669

Max Act: 0.3126. Min Act: -0.0000

Data Index: 1546405 (The Pile)

Max Activating Token Index: 923