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

Dataset: The Pile

Neuron 593 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: 0.0711. Min Range: -0.0711

Max Act: 0.0711. Min Act: -0.0000

Data Index: 322690 (The Pile)

Max Activating Token Index: 244

Text #1

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0640. Min Act: -0.0000

Data Index: 1641706 (The Pile)

Max Activating Token Index: 592

Text #2

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0655. Min Act: -0.0000

Data Index: 670891 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0584. Min Act: -0.0000

Data Index: 969385 (The Pile)

Max Activating Token Index: 198

Text #4

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0562. Min Act: -0.0000

Data Index: 852925 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0592. Min Act: -0.0000

Data Index: 1263728 (The Pile)

Max Activating Token Index: 316

Text #6

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0508. Min Act: -0.0000

Data Index: 565961 (The Pile)

Max Activating Token Index: 515

Text #7

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0378. Min Act: -0.0000

Data Index: 1232695 (The Pile)

Max Activating Token Index: 680

Text #8

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0492. Min Act: -0.0000

Data Index: 717107 (The Pile)

Max Activating Token Index: 963

Text #9

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0504. Min Act: -0.0000

Data Index: 1494219 (The Pile)

Max Activating Token Index: 827

Text #10

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0574. Min Act: -0.0000

Data Index: 71724 (The Pile)

Max Activating Token Index: 207

Text #11

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0494. Min Act: -0.0000

Data Index: 290675 (The Pile)

Max Activating Token Index: 393

Text #12

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0525. Min Act: -0.0000

Data Index: 547217 (The Pile)

Max Activating Token Index: 797

Text #13

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0484. Min Act: -0.0000

Data Index: 713491 (The Pile)

Max Activating Token Index: 973

Text #14

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0466. Min Act: -0.0000

Data Index: 121004 (The Pile)

Max Activating Token Index: 774

Text #15

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0440. Min Act: -0.0000

Data Index: 539654 (The Pile)

Max Activating Token Index: 833

Text #16

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0494. Min Act: -0.0000

Data Index: 1252520 (The Pile)

Max Activating Token Index: 507

Text #17

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0468. Min Act: -0.0000

Data Index: 320139 (The Pile)

Max Activating Token Index: 626

Text #18

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0477. Min Act: -0.0000

Data Index: 1287157 (The Pile)

Max Activating Token Index: 996

Text #19

Max Range: 0.0711. Min Range: -0.0711

Max Act: 0.0467. Min Act: -0.0000

Data Index: 192687 (The Pile)

Max Activating Token Index: 916