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

Dataset: The Pile

Neuron 80 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1156885 (The Pile)

Max Activating Token Index: 803

Text #1

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4732. Min Act: -0.0000

Data Index: 638668 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4344. Min Act: -0.0000

Data Index: 1039585 (The Pile)

Max Activating Token Index: 453

Text #3

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4586. Min Act: -0.0000

Data Index: 367271 (The Pile)

Max Activating Token Index: 618

Text #4

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1048923 (The Pile)

Max Activating Token Index: 128

Text #5

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1163537 (The Pile)

Max Activating Token Index: 261

Text #6

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4415. Min Act: -0.0000

Data Index: 77898 (The Pile)

Max Activating Token Index: 138

Text #7

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1205066 (The Pile)

Max Activating Token Index: 676

Text #8

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3887. Min Act: -0.0000

Data Index: 1698249 (The Pile)

Max Activating Token Index: 64

Text #9

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3857. Min Act: -0.0000

Data Index: 849582 (The Pile)

Max Activating Token Index: 754

Text #10

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3402. Min Act: -0.0000

Data Index: 597312 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.4214. Min Act: -0.0000

Data Index: 272536 (The Pile)

Max Activating Token Index: 851

Text #12

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3617. Min Act: 0.0000

Data Index: 1961680 (The Pile)

Max Activating Token Index: 437

Text #13

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3528. Min Act: -0.0000

Data Index: 701650 (The Pile)

Max Activating Token Index: 670

Text #14

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3680. Min Act: 0.0000

Data Index: 929341 (The Pile)

Max Activating Token Index: 767

Text #15

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3621. Min Act: -0.0000

Data Index: 881025 (The Pile)

Max Activating Token Index: 914

Text #16

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3753. Min Act: -0.0000

Data Index: 1945536 (The Pile)

Max Activating Token Index: 494

Text #17

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1019043 (The Pile)

Max Activating Token Index: 390

Text #18

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3271. Min Act: -0.0000

Data Index: 1329728 (The Pile)

Max Activating Token Index: 297

Text #19

Max Range: 0.4797. Min Range: -0.4797

Max Act: 0.3770. Min Act: 0.0001

Data Index: 448482 (The Pile)

Max Activating Token Index: 229