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

Dataset: The Pile

Neuron 2885 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: 0.8828. Min Range: -0.8828

Max Act: 0.8514. Min Act: -0.0000

Data Index: 749076 (The Pile)

Max Activating Token Index: 523

Text #1

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.8718. Min Act: -0.0000

Data Index: 231393 (The Pile)

Max Activating Token Index: 228

Text #2

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.8828. Min Act: -0.0000

Data Index: 650460 (The Pile)

Max Activating Token Index: 314

Text #3

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1418042 (The Pile)

Max Activating Token Index: 642

Text #4

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7503. Min Act: -0.0000

Data Index: 320017 (The Pile)

Max Activating Token Index: 451

Text #5

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7173. Min Act: -0.0000

Data Index: 452854 (The Pile)

Max Activating Token Index: 635

Text #6

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1689929 (The Pile)

Max Activating Token Index: 659

Text #7

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6838. Min Act: -0.0000

Data Index: 525880 (The Pile)

Max Activating Token Index: 951

Text #8

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1467241 (The Pile)

Max Activating Token Index: 121

Text #9

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1957410 (The Pile)

Max Activating Token Index: 766

Text #10

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6663. Min Act: -0.0000

Data Index: 178540 (The Pile)

Max Activating Token Index: 964

Text #11

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1366879 (The Pile)

Max Activating Token Index: 773

Text #12

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6748. Min Act: -0.0000

Data Index: 15835 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6484. Min Act: -0.0000

Data Index: 906653 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1220408 (The Pile)

Max Activating Token Index: 744

Text #15

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6298. Min Act: -0.0000

Data Index: 883065 (The Pile)

Max Activating Token Index: 72

Text #16

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6441. Min Act: -0.0000

Data Index: 555279 (The Pile)

Max Activating Token Index: 115

Text #17

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6854. Min Act: -0.0000

Data Index: 45075 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6307. Min Act: -0.0000

Data Index: 694636 (The Pile)

Max Activating Token Index: 537

Text #19

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1091980 (The Pile)

Max Activating Token Index: 117