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

Dataset: The Pile

Neuron 714 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: 1.3412. Min Range: -1.3412

Max Act: 1.3412. Min Act: -0.0000

Data Index: 323219 (The Pile)

Max Activating Token Index: 413

Text #1

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.2618. Min Act: -0.0000

Data Index: 1571368 (The Pile)

Max Activating Token Index: 329

Text #2

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.1500. Min Act: -0.0000

Data Index: 250482 (The Pile)

Max Activating Token Index: 786

Text #3

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.1190. Min Act: -0.0000

Data Index: 1679504 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.1094. Min Act: -0.0000

Data Index: 1601926 (The Pile)

Max Activating Token Index: 660

Text #5

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.1788. Min Act: -0.0000

Data Index: 618428 (The Pile)

Max Activating Token Index: 419

Text #6

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.0572. Min Act: -0.0000

Data Index: 523711 (The Pile)

Max Activating Token Index: 826

Text #7

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.0841. Min Act: -0.0000

Data Index: 429582 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.0351. Min Act: -0.0000

Data Index: 1206158 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.9987. Min Act: -0.0000

Data Index: 1768813 (The Pile)

Max Activating Token Index: 116

Text #10

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.0414. Min Act: -0.0000

Data Index: 1195166 (The Pile)

Max Activating Token Index: 996

Text #11

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.0694. Min Act: -0.0000

Data Index: 1929564 (The Pile)

Max Activating Token Index: 508

Text #12

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.0341. Min Act: -0.0000

Data Index: 849062 (The Pile)

Max Activating Token Index: 771

Text #13

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.0848. Min Act: -0.0000

Data Index: 942351 (The Pile)

Max Activating Token Index: 311

Text #14

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.0562. Min Act: -0.0000

Data Index: 1110476 (The Pile)

Max Activating Token Index: 849

Text #15

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.0103. Min Act: -0.0000

Data Index: 1971656 (The Pile)

Max Activating Token Index: 676

Text #16

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1421686 (The Pile)

Max Activating Token Index: 382

Text #17

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.9662. Min Act: -0.0000

Data Index: 982299 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.9425. Min Act: -0.0000

Data Index: 457366 (The Pile)

Max Activating Token Index: 348

Text #19

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.9283. Min Act: -0.0000

Data Index: 830879 (The Pile)

Max Activating Token Index: 346