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

Dataset: The Pile

Neuron 709 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.6624. Min Act: 0.0000

Data Index: 530773 (The Pile)

Max Activating Token Index: 173

Text #1

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.6089. Min Act: -0.0000

Data Index: 1820947 (The Pile)

Max Activating Token Index: 725

Text #2

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5960. Min Act: -0.0000

Data Index: 654369 (The Pile)

Max Activating Token Index: 357

Text #3

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5872. Min Act: -0.0000

Data Index: 144009 (The Pile)

Max Activating Token Index: 840

Text #4

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1692043 (The Pile)

Max Activating Token Index: 634

Text #5

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5805. Min Act: -0.0000

Data Index: 819190 (The Pile)

Max Activating Token Index: 726

Text #6

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1706336 (The Pile)

Max Activating Token Index: 485

Text #7

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1462034 (The Pile)

Max Activating Token Index: 752

Text #8

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5566. Min Act: 0.0000

Data Index: 1128477 (The Pile)

Max Activating Token Index: 604

Text #9

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.5415. Min Act: -0.0000

Data Index: 766661 (The Pile)

Max Activating Token Index: 802

Text #10

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1966064 (The Pile)

Max Activating Token Index: 417

Text #11

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1245324 (The Pile)

Max Activating Token Index: 363

Text #12

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1545500 (The Pile)

Max Activating Token Index: 501

Text #13

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1658699 (The Pile)

Max Activating Token Index: 342

Text #14

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4237. Min Act: -0.0000

Data Index: 164694 (The Pile)

Max Activating Token Index: 901

Text #15

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1054370 (The Pile)

Max Activating Token Index: 933

Text #16

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4453. Min Act: -0.0000

Data Index: 714959 (The Pile)

Max Activating Token Index: 491

Text #17

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4726. Min Act: -0.0000

Data Index: 957051 (The Pile)

Max Activating Token Index: 824

Text #18

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4591. Min Act: -0.0000

Data Index: 206020 (The Pile)

Max Activating Token Index: 370

Text #19

Max Range: 0.6624. Min Range: -0.6624

Max Act: 0.4545. Min Act: 0.0000

Data Index: 194321 (The Pile)

Max Activating Token Index: 284