Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2402 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1645155 (The Pile)

Max Activating Token Index: 907

Text #1

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.5516. Min Act: -0.0000

Data Index: 573836 (The Pile)

Max Activating Token Index: 961

Text #2

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.5489. Min Act: -0.0000

Data Index: 513236 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4988. Min Act: -0.0000

Data Index: 412356 (The Pile)

Max Activating Token Index: 728

Text #4

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1561573 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4938. Min Act: -0.0000

Data Index: 174300 (The Pile)

Max Activating Token Index: 390

Text #6

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4759. Min Act: 0.0000

Data Index: 537984 (The Pile)

Max Activating Token Index: 97

Text #7

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4597. Min Act: -0.0000

Data Index: 1291484 (The Pile)

Max Activating Token Index: 537

Text #8

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4716. Min Act: 0.0000

Data Index: 38486 (The Pile)

Max Activating Token Index: 945

Text #9

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1088128 (The Pile)

Max Activating Token Index: 1006

Text #10

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4504. Min Act: -0.0000

Data Index: 931756 (The Pile)

Max Activating Token Index: 391

Text #11

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4684. Min Act: -0.0000

Data Index: 747627 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4486. Min Act: 0.0000

Data Index: 563029 (The Pile)

Max Activating Token Index: 284

Text #13

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4633. Min Act: -0.0000

Data Index: 1880249 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1678014 (The Pile)

Max Activating Token Index: 638

Text #15

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4547. Min Act: -0.0000

Data Index: 200482 (The Pile)

Max Activating Token Index: 128

Text #16

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4649. Min Act: 0.0000

Data Index: 1852293 (The Pile)

Max Activating Token Index: 508

Text #17

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1605333 (The Pile)

Max Activating Token Index: 349

Text #18

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1260278 (The Pile)

Max Activating Token Index: 640

Text #19

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4344. Min Act: 0.0001

Data Index: 562366 (The Pile)

Max Activating Token Index: 111