Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1967 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.9090. Min Act: -0.0000

Data Index: 1680173 (The Pile)

Max Activating Token Index: 1014

Text #1

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1960508 (The Pile)

Max Activating Token Index: 387

Text #2

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.9372. Min Act: -0.0000

Data Index: 1515402 (The Pile)

Max Activating Token Index: 773

Text #3

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1424232 (The Pile)

Max Activating Token Index: 322

Text #4

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.8552. Min Act: -0.0000

Data Index: 136712 (The Pile)

Max Activating Token Index: 509

Text #5

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1509108 (The Pile)

Max Activating Token Index: 578

Text #6

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.8937. Min Act: -0.0000

Data Index: 88837 (The Pile)

Max Activating Token Index: 391

Text #7

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.7733. Min Act: -0.0000

Data Index: 421922 (The Pile)

Max Activating Token Index: 354

Text #8

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1151294 (The Pile)

Max Activating Token Index: 852

Text #9

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1279666 (The Pile)

Max Activating Token Index: 889

Text #10

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1316763 (The Pile)

Max Activating Token Index: 649

Text #11

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.7890. Min Act: -0.0000

Data Index: 112107 (The Pile)

Max Activating Token Index: 472

Text #12

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.7532. Min Act: -0.0000

Data Index: 879977 (The Pile)

Max Activating Token Index: 856

Text #13

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1364654 (The Pile)

Max Activating Token Index: 485

Text #14

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1977896 (The Pile)

Max Activating Token Index: 281

Text #15

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.7439. Min Act: -0.0000

Data Index: 372531 (The Pile)

Max Activating Token Index: 529

Text #16

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1092821 (The Pile)

Max Activating Token Index: 646

Text #17

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.7964. Min Act: -0.0000

Data Index: 1112246 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1180920 (The Pile)

Max Activating Token Index: 704

Text #19

Max Range: 0.9372. Min Range: -0.9372

Max Act: 0.7712. Min Act: -0.0000

Data Index: 846789 (The Pile)

Max Activating Token Index: 457