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

Dataset: The Pile

Neuron 1407 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: 0.4688. Min Range: -0.4688

Max Act: 0.4528. Min Act: -0.0000

Data Index: 388485 (The Pile)

Max Activating Token Index: 656

Text #1

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1087022 (The Pile)

Max Activating Token Index: 497

Text #2

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3751. Min Act: -0.0000

Data Index: 875869 (The Pile)

Max Activating Token Index: 864

Text #3

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.4012. Min Act: -0.0000

Data Index: 354203 (The Pile)

Max Activating Token Index: 215

Text #4

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3935. Min Act: -0.0000

Data Index: 361423 (The Pile)

Max Activating Token Index: 156

Text #5

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.4180. Min Act: -0.0000

Data Index: 262117 (The Pile)

Max Activating Token Index: 580

Text #6

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1278153 (The Pile)

Max Activating Token Index: 51

Text #7

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3568. Min Act: -0.0000

Data Index: 90157 (The Pile)

Max Activating Token Index: 39

Text #8

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1205642 (The Pile)

Max Activating Token Index: 135

Text #9

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3756. Min Act: -0.0000

Data Index: 619623 (The Pile)

Max Activating Token Index: 436

Text #10

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3864. Min Act: -0.0000

Data Index: 1477834 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3836. Min Act: -0.0000

Data Index: 420582 (The Pile)

Max Activating Token Index: 701

Text #12

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3647. Min Act: -0.0000

Data Index: 500844 (The Pile)

Max Activating Token Index: 578

Text #13

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1258577 (The Pile)

Max Activating Token Index: 270

Text #14

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1836335 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1127549 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1792315 (The Pile)

Max Activating Token Index: 872

Text #17

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3628. Min Act: -0.0000

Data Index: 203518 (The Pile)

Max Activating Token Index: 90

Text #18

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1126844 (The Pile)

Max Activating Token Index: 128

Text #19

Max Range: 0.4688. Min Range: -0.4688

Max Act: 0.3165. Min Act: -0.0000

Data Index: 800203 (The Pile)

Max Activating Token Index: 521