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

Dataset: The Pile

Neuron 1478 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: 1.3924. Min Range: -1.3924

Max Act: 1.3811. Min Act: -0.0000

Data Index: 1950648 (The Pile)

Max Activating Token Index: 438

Text #1

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.3924. Min Act: 0.0000

Data Index: 512451 (The Pile)

Max Activating Token Index: 218

Text #2

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.2025. Min Act: -0.0000

Data Index: 904615 (The Pile)

Max Activating Token Index: 835

Text #3

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.2837. Min Act: -0.0000

Data Index: 1547419 (The Pile)

Max Activating Token Index: 998

Text #4

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.2859. Min Act: -0.0000

Data Index: 1977188 (The Pile)

Max Activating Token Index: 645

Text #5

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.1721. Min Act: -0.0000

Data Index: 1269435 (The Pile)

Max Activating Token Index: 180

Text #6

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.2039. Min Act: -0.0000

Data Index: 1681320 (The Pile)

Max Activating Token Index: 854

Text #7

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.1362. Min Act: -0.0000

Data Index: 724526 (The Pile)

Max Activating Token Index: 682

Text #8

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.1626. Min Act: -0.0000

Data Index: 760924 (The Pile)

Max Activating Token Index: 801

Text #9

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.2209. Min Act: -0.0000

Data Index: 1531641 (The Pile)

Max Activating Token Index: 976

Text #10

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.1760. Min Act: -0.0000

Data Index: 290908 (The Pile)

Max Activating Token Index: 501

Text #11

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.1518. Min Act: -0.0000

Data Index: 59476 (The Pile)

Max Activating Token Index: 587

Text #12

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.1605. Min Act: -0.0000

Data Index: 1249759 (The Pile)

Max Activating Token Index: 388

Text #13

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.0927. Min Act: -0.0000

Data Index: 1385162 (The Pile)

Max Activating Token Index: 228

Text #14

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.1445. Min Act: -0.0000

Data Index: 1292334 (The Pile)

Max Activating Token Index: 460

Text #15

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.2054. Min Act: -0.0000

Data Index: 860747 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.1381. Min Act: -0.0000

Data Index: 113316 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.1859. Min Act: -0.0000

Data Index: 382629 (The Pile)

Max Activating Token Index: 711

Text #18

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.0811. Min Act: -0.0000

Data Index: 247442 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 1.3924. Min Range: -1.3924

Max Act: 1.0394. Min Act: -0.0000

Data Index: 1138562 (The Pile)

Max Activating Token Index: 140