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

Dataset: The Pile

Neuron 4789 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: 0.4412. Min Range: -0.4412

Max Act: 0.4400. Min Act: -0.0000

Data Index: 1953798 (The Pile)

Max Activating Token Index: 553

Text #1

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.4412. Min Act: -0.0000

Data Index: 300973 (The Pile)

Max Activating Token Index: 467

Text #2

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1803780 (The Pile)

Max Activating Token Index: 182

Text #3

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.4036. Min Act: -0.0001

Data Index: 1023618 (The Pile)

Max Activating Token Index: 843

Text #4

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1594068 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.4080. Min Act: -0.0000

Data Index: 982764 (The Pile)

Max Activating Token Index: 302

Text #6

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1169774 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1931847 (The Pile)

Max Activating Token Index: 650

Text #8

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3758. Min Act: -0.0000

Data Index: 677461 (The Pile)

Max Activating Token Index: 664

Text #9

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3947. Min Act: -0.0000

Data Index: 402389 (The Pile)

Max Activating Token Index: 428

Text #10

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3754. Min Act: -0.0000

Data Index: 849094 (The Pile)

Max Activating Token Index: 221

Text #11

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3594. Min Act: -0.0000

Data Index: 470933 (The Pile)

Max Activating Token Index: 483

Text #12

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3761. Min Act: -0.0000

Data Index: 161208 (The Pile)

Max Activating Token Index: 822

Text #13

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1637155 (The Pile)

Max Activating Token Index: 321

Text #14

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3551. Min Act: -0.0000

Data Index: 737457 (The Pile)

Max Activating Token Index: 618

Text #15

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3770. Min Act: -0.0000

Data Index: 130633 (The Pile)

Max Activating Token Index: 596

Text #16

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3511. Min Act: -0.0000

Data Index: 1257597 (The Pile)

Max Activating Token Index: 848

Text #17

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1084611 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3614. Min Act: -0.0000

Data Index: 950948 (The Pile)

Max Activating Token Index: 68

Text #19

Max Range: 0.4412. Min Range: -0.4412

Max Act: 0.3543. Min Act: -0.0000

Data Index: 847217 (The Pile)

Max Activating Token Index: 805