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

Dataset: The Pile

Neuron 1442 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.3312. Min Act: -0.0000

Data Index: 705577 (The Pile)

Max Activating Token Index: 354

Text #1

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.3231. Min Act: -0.0000

Data Index: 687030 (The Pile)

Max Activating Token Index: 826

Text #2

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.3221. Min Act: -0.0000

Data Index: 390508 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.3111. Min Act: -0.0000

Data Index: 1325965 (The Pile)

Max Activating Token Index: 721

Text #4

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.3110. Min Act: -0.0000

Data Index: 767893 (The Pile)

Max Activating Token Index: 124

Text #5

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1204042 (The Pile)

Max Activating Token Index: 762

Text #6

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1940167 (The Pile)

Max Activating Token Index: 156

Text #7

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.2728. Min Act: -0.0000

Data Index: 700032 (The Pile)

Max Activating Token Index: 798

Text #8

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1194179 (The Pile)

Max Activating Token Index: 991

Text #9

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.2633. Min Act: -0.0000

Data Index: 1559309 (The Pile)

Max Activating Token Index: 271

Text #10

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.2918. Min Act: -0.0000

Data Index: 660304 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.2696. Min Act: -0.0000

Data Index: 439399 (The Pile)

Max Activating Token Index: 68

Text #12

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1854875 (The Pile)

Max Activating Token Index: 917

Text #13

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.2643. Min Act: -0.0000

Data Index: 626997 (The Pile)

Max Activating Token Index: 850

Text #14

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.2547. Min Act: -0.0000

Data Index: 870521 (The Pile)

Max Activating Token Index: 47

Text #15

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.2591. Min Act: -0.0000

Data Index: 1669495 (The Pile)

Max Activating Token Index: 248

Text #16

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.2684. Min Act: -0.0000

Data Index: 1117519 (The Pile)

Max Activating Token Index: 519

Text #17

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.2551. Min Act: -0.0000

Data Index: 326703 (The Pile)

Max Activating Token Index: 313

Text #18

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.2542. Min Act: -0.0000

Data Index: 947741 (The Pile)

Max Activating Token Index: 443

Text #19

Max Range: 0.3312. Min Range: -0.3312

Max Act: 0.2453. Min Act: -0.0000

Data Index: 166898 (The Pile)

Max Activating Token Index: 616