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

Dataset: The Pile

Neuron 1468 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: 0.7890. Min Range: -0.7890

Max Act: 0.7766. Min Act: -0.0000

Data Index: 901657 (The Pile)

Max Activating Token Index: 961

Text #1

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.7022. Min Act: -0.0000

Data Index: 1824423 (The Pile)

Max Activating Token Index: 393

Text #2

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.7287. Min Act: -0.0000

Data Index: 210277 (The Pile)

Max Activating Token Index: 911

Text #3

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6791. Min Act: -0.0000

Data Index: 937985 (The Pile)

Max Activating Token Index: 571

Text #4

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1684850 (The Pile)

Max Activating Token Index: 520

Text #5

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.7890. Min Act: -0.0000

Data Index: 13085 (The Pile)

Max Activating Token Index: 738

Text #6

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1055638 (The Pile)

Max Activating Token Index: 397

Text #7

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6320. Min Act: -0.0000

Data Index: 832310 (The Pile)

Max Activating Token Index: 631

Text #8

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6221. Min Act: -0.0000

Data Index: 424459 (The Pile)

Max Activating Token Index: 523

Text #9

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1622525 (The Pile)

Max Activating Token Index: 852

Text #10

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6320. Min Act: -0.0000

Data Index: 159870 (The Pile)

Max Activating Token Index: 413

Text #11

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.5844. Min Act: -0.0000

Data Index: 377387 (The Pile)

Max Activating Token Index: 897

Text #12

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1294609 (The Pile)

Max Activating Token Index: 544

Text #13

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1417662 (The Pile)

Max Activating Token Index: 64

Text #14

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6554. Min Act: -0.0000

Data Index: 789450 (The Pile)

Max Activating Token Index: 57

Text #15

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6524. Min Act: -0.0000

Data Index: 590296 (The Pile)

Max Activating Token Index: 903

Text #16

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1263180 (The Pile)

Max Activating Token Index: 820

Text #17

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.6320. Min Act: -0.0000

Data Index: 968811 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.5621. Min Act: -0.0000

Data Index: 34774 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.5784. Min Act: -0.0000

Data Index: 12646 (The Pile)

Max Activating Token Index: 451