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

Dataset: The Pile

Neuron 4004 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: 1.3844. Min Range: -1.3844

Max Act: 1.2075. Min Act: -0.0000

Data Index: 996887 (The Pile)

Max Activating Token Index: 805

Text #1

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.3186. Min Act: -0.0000

Data Index: 880928 (The Pile)

Max Activating Token Index: 350

Text #2

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.3844. Min Act: -0.0000

Data Index: 1461524 (The Pile)

Max Activating Token Index: 561

Text #3

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.3701. Min Act: -0.0000

Data Index: 1144459 (The Pile)

Max Activating Token Index: 738

Text #4

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.2288. Min Act: -0.0000

Data Index: 1386660 (The Pile)

Max Activating Token Index: 673

Text #5

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.2876. Min Act: -0.0000

Data Index: 1566313 (The Pile)

Max Activating Token Index: 588

Text #6

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.1957. Min Act: -0.0000

Data Index: 403250 (The Pile)

Max Activating Token Index: 341

Text #7

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.3376. Min Act: -0.0000

Data Index: 319893 (The Pile)

Max Activating Token Index: 649

Text #8

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.2508. Min Act: -0.0000

Data Index: 1556103 (The Pile)

Max Activating Token Index: 408

Text #9

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.3114. Min Act: -0.0000

Data Index: 1347986 (The Pile)

Max Activating Token Index: 155

Text #10

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.1456. Min Act: -0.0000

Data Index: 343355 (The Pile)

Max Activating Token Index: 546

Text #11

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.2820. Min Act: -0.0000

Data Index: 378223 (The Pile)

Max Activating Token Index: 660

Text #12

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.1339. Min Act: -0.0000

Data Index: 1225737 (The Pile)

Max Activating Token Index: 682

Text #13

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.2729. Min Act: -0.0000

Data Index: 817548 (The Pile)

Max Activating Token Index: 787

Text #14

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.1111. Min Act: -0.0000

Data Index: 485212 (The Pile)

Max Activating Token Index: 229

Text #15

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.2795. Min Act: -0.0000

Data Index: 1783557 (The Pile)

Max Activating Token Index: 735

Text #16

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.0036. Min Act: -0.0000

Data Index: 1381257 (The Pile)

Max Activating Token Index: 767

Text #17

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.1995. Min Act: -0.0000

Data Index: 1897923 (The Pile)

Max Activating Token Index: 186

Text #18

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.1279. Min Act: -0.0000

Data Index: 958829 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 1.3844. Min Range: -1.3844

Max Act: 1.0690. Min Act: -0.0000

Data Index: 1573068 (The Pile)

Max Activating Token Index: 567