Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1556 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.3566. Min Act: -0.0000

Data Index: 1657419 (The Pile)

Max Activating Token Index: 337

Text #1

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.0601. Min Act: -0.0000

Data Index: 1433133 (The Pile)

Max Activating Token Index: 439

Text #2

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.2025. Min Act: -0.0000

Data Index: 791370 (The Pile)

Max Activating Token Index: 373

Text #3

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.0486. Min Act: -0.0000

Data Index: 369891 (The Pile)

Max Activating Token Index: 321

Text #4

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.0356. Min Act: -0.0000

Data Index: 569686 (The Pile)

Max Activating Token Index: 650

Text #5

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.0295. Min Act: -0.0000

Data Index: 497058 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.0067. Min Act: -0.0000

Data Index: 1983587 (The Pile)

Max Activating Token Index: 468

Text #7

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.6969. Min Act: -0.0000

Data Index: 930962 (The Pile)

Max Activating Token Index: 489

Text #8

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.6772. Min Act: -0.0000

Data Index: 1060819 (The Pile)

Max Activating Token Index: 318

Text #9

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.0651. Min Act: -0.0000

Data Index: 365675 (The Pile)

Max Activating Token Index: 243

Text #10

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.0480. Min Act: -0.0000

Data Index: 269802 (The Pile)

Max Activating Token Index: 197

Text #11

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.7670. Min Act: -0.0000

Data Index: 902268 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.9035. Min Act: -0.0000

Data Index: 168388 (The Pile)

Max Activating Token Index: 439

Text #13

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.8849. Min Act: -0.0000

Data Index: 1984065 (The Pile)

Max Activating Token Index: 47

Text #14

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.9069. Min Act: -0.0000

Data Index: 1993091 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.8916. Min Act: -0.0000

Data Index: 564289 (The Pile)

Max Activating Token Index: 268

Text #16

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.6284. Min Act: -0.0000

Data Index: 1389848 (The Pile)

Max Activating Token Index: 623

Text #17

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.7526. Min Act: -0.0000

Data Index: 466619 (The Pile)

Max Activating Token Index: 679

Text #18

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.0010. Min Act: -0.0000

Data Index: 539092 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.8485. Min Act: -0.0000

Data Index: 1181411 (The Pile)

Max Activating Token Index: 592