Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2389 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1744361 (The Pile)

Max Activating Token Index: 123

Text #1

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4338. Min Act: -0.0000

Data Index: 1999576 (The Pile)

Max Activating Token Index: 373

Text #2

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1793114 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3964. Min Act: -0.0000

Data Index: 497810 (The Pile)

Max Activating Token Index: 558

Text #4

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4099. Min Act: -0.0000

Data Index: 851559 (The Pile)

Max Activating Token Index: 85

Text #5

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.4033. Min Act: -0.0000

Data Index: 852684 (The Pile)

Max Activating Token Index: 29

Text #6

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3689. Min Act: -0.0000

Data Index: 939387 (The Pile)

Max Activating Token Index: 416

Text #7

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3949. Min Act: -0.0000

Data Index: 361248 (The Pile)

Max Activating Token Index: 424

Text #8

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1526680 (The Pile)

Max Activating Token Index: 149

Text #9

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3903. Min Act: -0.0000

Data Index: 1218773 (The Pile)

Max Activating Token Index: 221

Text #10

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3657. Min Act: -0.0000

Data Index: 429334 (The Pile)

Max Activating Token Index: 729

Text #11

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3869. Min Act: -0.0000

Data Index: 109336 (The Pile)

Max Activating Token Index: 42

Text #12

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3586. Min Act: -0.0000

Data Index: 741489 (The Pile)

Max Activating Token Index: 48

Text #13

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3816. Min Act: -0.0000

Data Index: 628379 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3508. Min Act: -0.0000

Data Index: 381973 (The Pile)

Max Activating Token Index: 356

Text #15

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3861. Min Act: -0.0000

Data Index: 406583 (The Pile)

Max Activating Token Index: 944

Text #16

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3485. Min Act: -0.0000

Data Index: 672420 (The Pile)

Max Activating Token Index: 532

Text #17

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3562. Min Act: -0.0000

Data Index: 1757590 (The Pile)

Max Activating Token Index: 349

Text #18

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1462519 (The Pile)

Max Activating Token Index: 330

Text #19

Max Range: 0.4603. Min Range: -0.4603

Max Act: 0.3534. Min Act: -0.0000

Data Index: 697922 (The Pile)

Max Activating Token Index: 720