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

Dataset: The Pile

Neuron 2647 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: 0.4077. Min Range: -0.4077

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1005810 (The Pile)

Max Activating Token Index: 909

Text #1

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.4077. Min Act: -0.0000

Data Index: 570881 (The Pile)

Max Activating Token Index: 733

Text #2

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1732237 (The Pile)

Max Activating Token Index: 22

Text #3

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1333814 (The Pile)

Max Activating Token Index: 245

Text #4

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3919. Min Act: -0.0000

Data Index: 192416 (The Pile)

Max Activating Token Index: 289

Text #5

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.4036. Min Act: -0.0000

Data Index: 1000641 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3687. Min Act: -0.0000

Data Index: 629671 (The Pile)

Max Activating Token Index: 578

Text #7

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3581. Min Act: -0.0000

Data Index: 257723 (The Pile)

Max Activating Token Index: 333

Text #8

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3539. Min Act: -0.0000

Data Index: 482454 (The Pile)

Max Activating Token Index: 938

Text #9

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1480546 (The Pile)

Max Activating Token Index: 344

Text #10

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3156. Min Act: -0.0000

Data Index: 1159982 (The Pile)

Max Activating Token Index: 341

Text #11

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3348. Min Act: -0.0000

Data Index: 1537787 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3382. Min Act: -0.0000

Data Index: 1996021 (The Pile)

Max Activating Token Index: 15

Text #13

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1935924 (The Pile)

Max Activating Token Index: 664

Text #14

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.2807. Min Act: -0.0000

Data Index: 611556 (The Pile)

Max Activating Token Index: 685

Text #15

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3332. Min Act: -0.0000

Data Index: 1755501 (The Pile)

Max Activating Token Index: 223

Text #16

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1402866 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1368232 (The Pile)

Max Activating Token Index: 351

Text #18

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3079. Min Act: -0.0000

Data Index: 142175 (The Pile)

Max Activating Token Index: 681

Text #19

Max Range: 0.4077. Min Range: -0.4077

Max Act: 0.3157. Min Act: -0.0000

Data Index: 761955 (The Pile)

Max Activating Token Index: 556