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

Dataset: The Pile

Neuron 1549 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: 1.5480. Min Range: -1.5480

Max Act: 1.5480. Min Act: -0.0000

Data Index: 504541 (The Pile)

Max Activating Token Index: 268

Text #1

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.3264. Min Act: -0.0000

Data Index: 616399 (The Pile)

Max Activating Token Index: 458

Text #2

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.2888. Min Act: -0.0000

Data Index: 807525 (The Pile)

Max Activating Token Index: 848

Text #3

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.1937. Min Act: -0.0000

Data Index: 302441 (The Pile)

Max Activating Token Index: 546

Text #4

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1563308 (The Pile)

Max Activating Token Index: 922

Text #5

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.0926. Min Act: -0.0000

Data Index: 1194871 (The Pile)

Max Activating Token Index: 265

Text #6

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.2261. Min Act: -0.0000

Data Index: 571944 (The Pile)

Max Activating Token Index: 111

Text #7

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.0444. Min Act: -0.0000

Data Index: 2149 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.1505. Min Act: -0.0000

Data Index: 1352593 (The Pile)

Max Activating Token Index: 757

Text #9

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.0822. Min Act: -0.0000

Data Index: 834899 (The Pile)

Max Activating Token Index: 705

Text #10

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.1658. Min Act: -0.0000

Data Index: 959928 (The Pile)

Max Activating Token Index: 469

Text #11

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.1558. Min Act: -0.0000

Data Index: 860333 (The Pile)

Max Activating Token Index: 310

Text #12

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.1934. Min Act: -0.0000

Data Index: 1460697 (The Pile)

Max Activating Token Index: 865

Text #13

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.0733. Min Act: -0.0000

Data Index: 1187718 (The Pile)

Max Activating Token Index: 473

Text #14

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.0857. Min Act: -0.0000

Data Index: 691469 (The Pile)

Max Activating Token Index: 889

Text #15

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.0445. Min Act: -0.0000

Data Index: 1692527 (The Pile)

Max Activating Token Index: 537

Text #16

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.0406. Min Act: -0.0000

Data Index: 709453 (The Pile)

Max Activating Token Index: 560

Text #17

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.0373. Min Act: -0.0000

Data Index: 6589 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.0899. Min Act: -0.0000

Data Index: 633433 (The Pile)

Max Activating Token Index: 477

Text #19

Max Range: 1.5480. Min Range: -1.5480

Max Act: 1.1365. Min Act: -0.0000

Data Index: 1458489 (The Pile)

Max Activating Token Index: 238