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

Dataset: The Pile

Neuron 2796 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.1020. Min Range: -3.1020

Max Act: 3.1020. Min Act: -0.0000

Data Index: 569429 (The Pile)

Max Activating Token Index: 399

Text #1

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.8085. Min Act: -0.0000

Data Index: 169399 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.7700. Min Act: -0.0000

Data Index: 1782069 (The Pile)

Max Activating Token Index: 383

Text #3

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.4881. Min Act: -0.0000

Data Index: 1158084 (The Pile)

Max Activating Token Index: 39

Text #4

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.4976. Min Act: -0.0000

Data Index: 1892336 (The Pile)

Max Activating Token Index: 77

Text #5

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.7493. Min Act: -0.0000

Data Index: 1608799 (The Pile)

Max Activating Token Index: 232

Text #6

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.8567. Min Act: -0.0000

Data Index: 362815 (The Pile)

Max Activating Token Index: 33

Text #7

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.9854. Min Act: -0.0000

Data Index: 995397 (The Pile)

Max Activating Token Index: 780

Text #8

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.6424. Min Act: -0.0000

Data Index: 956962 (The Pile)

Max Activating Token Index: 91

Text #9

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.6722. Min Act: -0.0000

Data Index: 40156 (The Pile)

Max Activating Token Index: 483

Text #10

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.3873. Min Act: -0.0000

Data Index: 173332 (The Pile)

Max Activating Token Index: 547

Text #11

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.3834. Min Act: -0.0000

Data Index: 1229159 (The Pile)

Max Activating Token Index: 886

Text #12

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.5215. Min Act: -0.0000

Data Index: 393717 (The Pile)

Max Activating Token Index: 439

Text #13

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.3861. Min Act: -0.0000

Data Index: 128841 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.3547. Min Act: -0.0000

Data Index: 835869 (The Pile)

Max Activating Token Index: 769

Text #15

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.4680. Min Act: -0.0000

Data Index: 1783123 (The Pile)

Max Activating Token Index: 442

Text #16

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.4138. Min Act: -0.0000

Data Index: 17669 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.4178. Min Act: -0.0000

Data Index: 1952586 (The Pile)

Max Activating Token Index: 789

Text #18

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.3541. Min Act: -0.0000

Data Index: 1965132 (The Pile)

Max Activating Token Index: 655

Text #19

Max Range: 3.1020. Min Range: -3.1020

Max Act: 2.3589. Min Act: -0.0000

Data Index: 1657571 (The Pile)

Max Activating Token Index: 355