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

Dataset: The Pile

Neuron 363 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1059769 (The Pile)

Max Activating Token Index: 731

Text #1

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.4283. Min Act: -0.0000

Data Index: 1924001 (The Pile)

Max Activating Token Index: 418

Text #2

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.4392. Min Act: -0.0000

Data Index: 688402 (The Pile)

Max Activating Token Index: 927

Text #3

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3969. Min Act: -0.0000

Data Index: 1295870 (The Pile)

Max Activating Token Index: 406

Text #4

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3809. Min Act: -0.0000

Data Index: 617318 (The Pile)

Max Activating Token Index: 420

Text #5

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3912. Min Act: -0.0000

Data Index: 722654 (The Pile)

Max Activating Token Index: 82

Text #6

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3810. Min Act: -0.0000

Data Index: 527349 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3512. Min Act: -0.0000

Data Index: 382492 (The Pile)

Max Activating Token Index: 657

Text #8

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3619. Min Act: -0.0000

Data Index: 347696 (The Pile)

Max Activating Token Index: 37

Text #9

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3851. Min Act: -0.0000

Data Index: 68637 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3633. Min Act: -0.0000

Data Index: 558675 (The Pile)

Max Activating Token Index: 266

Text #11

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3443. Min Act: -0.0000

Data Index: 806259 (The Pile)

Max Activating Token Index: 964

Text #12

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1584000 (The Pile)

Max Activating Token Index: 296

Text #13

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1097539 (The Pile)

Max Activating Token Index: 532

Text #14

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1235995 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1788399 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1670578 (The Pile)

Max Activating Token Index: 55

Text #17

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3403. Min Act: -0.0000

Data Index: 64341 (The Pile)

Max Activating Token Index: 246

Text #18

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1886316 (The Pile)

Max Activating Token Index: 432

Text #19

Max Range: 0.4536. Min Range: -0.4536

Max Act: 0.3504. Min Act: -0.0000

Data Index: 747153 (The Pile)

Max Activating Token Index: 88