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

Dataset: The Pile

Neuron 2990 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: 0.4524. Min Range: -0.4524

Max Act: 0.4386. Min Act: -0.0000

Data Index: 690573 (The Pile)

Max Activating Token Index: 168

Text #1

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.4275. Min Act: -0.0000

Data Index: 1837108 (The Pile)

Max Activating Token Index: 368

Text #2

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.4524. Min Act: -0.0000

Data Index: 28420 (The Pile)

Max Activating Token Index: 440

Text #3

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.4101. Min Act: -0.0000

Data Index: 1567114 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3147. Min Act: -0.0000

Data Index: 1172116 (The Pile)

Max Activating Token Index: 532

Text #5

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1898722 (The Pile)

Max Activating Token Index: 411

Text #6

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3803. Min Act: -0.0000

Data Index: 616455 (The Pile)

Max Activating Token Index: 653

Text #7

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3572. Min Act: -0.0000

Data Index: 237076 (The Pile)

Max Activating Token Index: 269

Text #8

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3778. Min Act: -0.0000

Data Index: 214761 (The Pile)

Max Activating Token Index: 254

Text #9

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1903839 (The Pile)

Max Activating Token Index: 450

Text #10

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3666. Min Act: -0.0000

Data Index: 757861 (The Pile)

Max Activating Token Index: 702

Text #11

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3727. Min Act: -0.0000

Data Index: 768972 (The Pile)

Max Activating Token Index: 764

Text #12

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3594. Min Act: -0.0000

Data Index: 1959141 (The Pile)

Max Activating Token Index: 948

Text #13

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3527. Min Act: -0.0000

Data Index: 19519 (The Pile)

Max Activating Token Index: 522

Text #14

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1475648 (The Pile)

Max Activating Token Index: 536

Text #15

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1539448 (The Pile)

Max Activating Token Index: 120

Text #16

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3282. Min Act: -0.0000

Data Index: 223545 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3367. Min Act: -0.0000

Data Index: 337623 (The Pile)

Max Activating Token Index: 703

Text #18

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1091783 (The Pile)

Max Activating Token Index: 939

Text #19

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3389. Min Act: -0.0000

Data Index: 381463 (The Pile)

Max Activating Token Index: 1014