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

Dataset: The Pile

Neuron 2378 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: 0.8754. Min Range: -0.8754

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1950981 (The Pile)

Max Activating Token Index: 698

Text #1

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.8754. Min Act: -0.0000

Data Index: 525812 (The Pile)

Max Activating Token Index: 523

Text #2

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1222566 (The Pile)

Max Activating Token Index: 733

Text #3

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7920. Min Act: -0.0000

Data Index: 403016 (The Pile)

Max Activating Token Index: 472

Text #4

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1333576 (The Pile)

Max Activating Token Index: 656

Text #5

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.8287. Min Act: -0.0000

Data Index: 810201 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7895. Min Act: -0.0000

Data Index: 682287 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1684110 (The Pile)

Max Activating Token Index: 256

Text #8

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1569696 (The Pile)

Max Activating Token Index: 123

Text #9

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7711. Min Act: -0.0000

Data Index: 761633 (The Pile)

Max Activating Token Index: 516

Text #10

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7521. Min Act: -0.0000

Data Index: 1322816 (The Pile)

Max Activating Token Index: 203

Text #11

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7483. Min Act: -0.0000

Data Index: 1170802 (The Pile)

Max Activating Token Index: 194

Text #12

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7209. Min Act: -0.0000

Data Index: 963370 (The Pile)

Max Activating Token Index: 351

Text #13

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1896221 (The Pile)

Max Activating Token Index: 64

Text #14

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1889385 (The Pile)

Max Activating Token Index: 489

Text #15

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7211. Min Act: -0.0000

Data Index: 1161586 (The Pile)

Max Activating Token Index: 581

Text #16

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7088. Min Act: -0.0000

Data Index: 1172091 (The Pile)

Max Activating Token Index: 302

Text #17

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7156. Min Act: -0.0000

Data Index: 396050 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.6886. Min Act: -0.0000

Data Index: 128243 (The Pile)

Max Activating Token Index: 415

Text #19

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1218337 (The Pile)

Max Activating Token Index: 370