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

Dataset: The Pile

Neuron 4588 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.8307. Min Act: -0.0000

Data Index: 915584 (The Pile)

Max Activating Token Index: 301

Text #1

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.7689. Min Act: -0.0000

Data Index: 1706312 (The Pile)

Max Activating Token Index: 772

Text #2

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.7751. Min Act: -0.0000

Data Index: 335518 (The Pile)

Max Activating Token Index: 338

Text #3

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.5615. Min Act: -0.0000

Data Index: 1100937 (The Pile)

Max Activating Token Index: 493

Text #4

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.8197. Min Act: -0.0000

Data Index: 1049377 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.6131. Min Act: -0.0000

Data Index: 1058825 (The Pile)

Max Activating Token Index: 448

Text #6

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.7133. Min Act: -0.0000

Data Index: 1971754 (The Pile)

Max Activating Token Index: 885

Text #7

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.6696. Min Act: -0.0000

Data Index: 1453227 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.5770. Min Act: -0.0000

Data Index: 285583 (The Pile)

Max Activating Token Index: 482

Text #9

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.6739. Min Act: -0.0000

Data Index: 41383 (The Pile)

Max Activating Token Index: 255

Text #10

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.6560. Min Act: -0.0000

Data Index: 1238431 (The Pile)

Max Activating Token Index: 392

Text #11

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.5936. Min Act: -0.0000

Data Index: 1055122 (The Pile)

Max Activating Token Index: 508

Text #12

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.4960. Min Act: -0.0000

Data Index: 1996699 (The Pile)

Max Activating Token Index: 366

Text #13

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.5936. Min Act: -0.0000

Data Index: 10744 (The Pile)

Max Activating Token Index: 358

Text #14

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.5719. Min Act: -0.0000

Data Index: 298932 (The Pile)

Max Activating Token Index: 389

Text #15

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.6491. Min Act: -0.0000

Data Index: 1915527 (The Pile)

Max Activating Token Index: 253

Text #16

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.4965. Min Act: -0.0000

Data Index: 925867 (The Pile)

Max Activating Token Index: 916

Text #17

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.5564. Min Act: -0.0000

Data Index: 291412 (The Pile)

Max Activating Token Index: 611

Text #18

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.5412. Min Act: -0.0000

Data Index: 1950988 (The Pile)

Max Activating Token Index: 435

Text #19

Max Range: 1.8307. Min Range: -1.8307

Max Act: 1.5530. Min Act: -0.0000

Data Index: 1446928 (The Pile)

Max Activating Token Index: 711