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

Dataset: The Pile

Neuron 4738 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1820094 (The Pile)

Max Activating Token Index: 86

Text #1

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.5410. Min Act: -0.0000

Data Index: 513061 (The Pile)

Max Activating Token Index: 301

Text #2

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4406. Min Act: -0.0000

Data Index: 366583 (The Pile)

Max Activating Token Index: 234

Text #3

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4310. Min Act: -0.0000

Data Index: 770264 (The Pile)

Max Activating Token Index: 490

Text #4

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4251. Min Act: -0.0000

Data Index: 879415 (The Pile)

Max Activating Token Index: 690

Text #5

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1938573 (The Pile)

Max Activating Token Index: 339

Text #6

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3887. Min Act: -0.0000

Data Index: 879610 (The Pile)

Max Activating Token Index: 750

Text #7

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4117. Min Act: -0.0000

Data Index: 861716 (The Pile)

Max Activating Token Index: 576

Text #8

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3472. Min Act: -0.0000

Data Index: 527978 (The Pile)

Max Activating Token Index: 619

Text #9

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3827. Min Act: -0.0000

Data Index: 166530 (The Pile)

Max Activating Token Index: 217

Text #10

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3820. Min Act: -0.0000

Data Index: 372363 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3560. Min Act: -0.0000

Data Index: 336917 (The Pile)

Max Activating Token Index: 443

Text #12

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1035968 (The Pile)

Max Activating Token Index: 289

Text #13

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1919839 (The Pile)

Max Activating Token Index: 632

Text #14

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3732. Min Act: -0.0000

Data Index: 979846 (The Pile)

Max Activating Token Index: 400

Text #15

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1569886 (The Pile)

Max Activating Token Index: 713

Text #16

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3708. Min Act: -0.0000

Data Index: 901296 (The Pile)

Max Activating Token Index: 279

Text #17

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3440. Min Act: -0.0000

Data Index: 1148078 (The Pile)

Max Activating Token Index: 457

Text #18

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3633. Min Act: -0.0000

Data Index: 954865 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.3492. Min Act: -0.0000

Data Index: 660347 (The Pile)

Max Activating Token Index: 555