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

Dataset: The Pile

Neuron 1862 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1251. Min Range: -1.1251

Max Act: 1.1251. Min Act: -0.0000

Data Index: 1617771 (The Pile)

Max Activating Token Index: 351

Text #1

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.8843. Min Act: -0.0000

Data Index: 497032 (The Pile)

Max Activating Token Index: 329

Text #2

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.8227. Min Act: -0.0000

Data Index: 287369 (The Pile)

Max Activating Token Index: 611

Text #3

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.8057. Min Act: -0.0000

Data Index: 804589 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.7439. Min Act: -0.0000

Data Index: 471420 (The Pile)

Max Activating Token Index: 1019

Text #5

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.7962. Min Act: -0.0000

Data Index: 927004 (The Pile)

Max Activating Token Index: 948

Text #6

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.7658. Min Act: -0.0000

Data Index: 969831 (The Pile)

Max Activating Token Index: 416

Text #7

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.7180. Min Act: -0.0000

Data Index: 489741 (The Pile)

Max Activating Token Index: 583

Text #8

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.7622. Min Act: -0.0000

Data Index: 1400809 (The Pile)

Max Activating Token Index: 835

Text #9

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.7063. Min Act: -0.0000

Data Index: 707045 (The Pile)

Max Activating Token Index: 207

Text #10

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.7102. Min Act: -0.0000

Data Index: 1801591 (The Pile)

Max Activating Token Index: 360

Text #11

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.6523. Min Act: -0.0000

Data Index: 977987 (The Pile)

Max Activating Token Index: 371

Text #12

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1176695 (The Pile)

Max Activating Token Index: 368

Text #13

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.6690. Min Act: -0.0000

Data Index: 303863 (The Pile)

Max Activating Token Index: 218

Text #14

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.6845. Min Act: -0.0000

Data Index: 216004 (The Pile)

Max Activating Token Index: 225

Text #15

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1251150 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1436090 (The Pile)

Max Activating Token Index: 620

Text #17

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1801267 (The Pile)

Max Activating Token Index: 361

Text #18

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.5083. Min Act: -0.0001

Data Index: 1733391 (The Pile)

Max Activating Token Index: 718

Text #19

Max Range: 1.1251. Min Range: -1.1251

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1516145 (The Pile)

Max Activating Token Index: 636