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

Dataset: The Pile

Neuron 4097 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: 0.5022. Min Range: -0.5022

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1570639 (The Pile)

Max Activating Token Index: 56

Text #1

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.4641. Min Act: -0.0000

Data Index: 168031 (The Pile)

Max Activating Token Index: 311

Text #2

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1609527 (The Pile)

Max Activating Token Index: 685

Text #3

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3959. Min Act: -0.0000

Data Index: 710382 (The Pile)

Max Activating Token Index: 304

Text #4

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3695. Min Act: -0.0000

Data Index: 733816 (The Pile)

Max Activating Token Index: 377

Text #5

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3324. Min Act: -0.0000

Data Index: 95843 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1532231 (The Pile)

Max Activating Token Index: 648

Text #7

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1579834 (The Pile)

Max Activating Token Index: 156

Text #8

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1871758 (The Pile)

Max Activating Token Index: 466

Text #9

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3429. Min Act: -0.0000

Data Index: 1483677 (The Pile)

Max Activating Token Index: 384

Text #10

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3156. Min Act: -0.0000

Data Index: 1272425 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3417. Min Act: -0.0000

Data Index: 306450 (The Pile)

Max Activating Token Index: 234

Text #12

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3280. Min Act: -0.0000

Data Index: 1922697 (The Pile)

Max Activating Token Index: 820

Text #13

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.2780. Min Act: -0.0000

Data Index: 638148 (The Pile)

Max Activating Token Index: 255

Text #14

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3294. Min Act: -0.0000

Data Index: 552297 (The Pile)

Max Activating Token Index: 368

Text #15

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3238. Min Act: -0.0000

Data Index: 561404 (The Pile)

Max Activating Token Index: 543

Text #16

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.3101. Min Act: -0.0000

Data Index: 856841 (The Pile)

Max Activating Token Index: 505

Text #17

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.2441. Min Act: -0.0000

Data Index: 1775727 (The Pile)

Max Activating Token Index: 924

Text #18

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.2561. Min Act: -0.0000

Data Index: 459030 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 0.5022. Min Range: -0.5022

Max Act: 0.2878. Min Act: -0.0000

Data Index: 352716 (The Pile)

Max Activating Token Index: 889