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

Dataset: The Pile

Neuron 3305 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: 0.9848. Min Range: -0.9848

Max Act: 0.9577. Min Act: -0.0000

Data Index: 737687 (The Pile)

Max Activating Token Index: 923

Text #1

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.9513. Min Act: -0.0000

Data Index: 410483 (The Pile)

Max Activating Token Index: 867

Text #2

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.9848. Min Act: -0.0000

Data Index: 591445 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.9527. Min Act: -0.0000

Data Index: 33533 (The Pile)

Max Activating Token Index: 790

Text #4

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.9580. Min Act: -0.0000

Data Index: 1975300 (The Pile)

Max Activating Token Index: 927

Text #5

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.8953. Min Act: -0.0000

Data Index: 347562 (The Pile)

Max Activating Token Index: 926

Text #6

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7995. Min Act: -0.0000

Data Index: 625941 (The Pile)

Max Activating Token Index: 353

Text #7

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7942. Min Act: -0.0000

Data Index: 640023 (The Pile)

Max Activating Token Index: 455

Text #8

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7599. Min Act: -0.0000

Data Index: 761005 (The Pile)

Max Activating Token Index: 811

Text #9

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.8252. Min Act: -0.0000

Data Index: 820887 (The Pile)

Max Activating Token Index: 624

Text #10

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7693. Min Act: -0.0000

Data Index: 1256549 (The Pile)

Max Activating Token Index: 631

Text #11

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7393. Min Act: -0.0000

Data Index: 1988600 (The Pile)

Max Activating Token Index: 53

Text #12

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1435584 (The Pile)

Max Activating Token Index: 383

Text #13

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7818. Min Act: -0.0000

Data Index: 719807 (The Pile)

Max Activating Token Index: 537

Text #14

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1144685 (The Pile)

Max Activating Token Index: 449

Text #15

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1565193 (The Pile)

Max Activating Token Index: 819

Text #16

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1751396 (The Pile)

Max Activating Token Index: 604

Text #17

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1977268 (The Pile)

Max Activating Token Index: 613

Text #18

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.6597. Min Act: -0.0000

Data Index: 1697900 (The Pile)

Max Activating Token Index: 418

Text #19

Max Range: 0.9848. Min Range: -0.9848

Max Act: 0.6933. Min Act: -0.0000

Data Index: 657367 (The Pile)

Max Activating Token Index: 625