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

Dataset: The Pile

Neuron 430 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: 3.6634. Min Range: -3.6634

Max Act: 3.5546. Min Act: -0.0000

Data Index: 1858708 (The Pile)

Max Activating Token Index: 349

Text #1

Max Range: 3.6634. Min Range: -3.6634

Max Act: 3.6634. Min Act: -0.0000

Data Index: 1008039 (The Pile)

Max Activating Token Index: 119

Text #2

Max Range: 3.6634. Min Range: -3.6634

Max Act: 3.2191. Min Act: -0.0000

Data Index: 509945 (The Pile)

Max Activating Token Index: 735

Text #3

Max Range: 3.6634. Min Range: -3.6634

Max Act: 3.1280. Min Act: -0.0000

Data Index: 885754 (The Pile)

Max Activating Token Index: 127

Text #4

Max Range: 3.6634. Min Range: -3.6634

Max Act: 2.9905. Min Act: -0.0000

Data Index: 1160219 (The Pile)

Max Activating Token Index: 992

Text #5

Max Range: 3.6634. Min Range: -3.6634

Max Act: 3.1395. Min Act: -0.0000

Data Index: 1777985 (The Pile)

Max Activating Token Index: 523

Text #6

Max Range: 3.6634. Min Range: -3.6634

Max Act: 2.9152. Min Act: -0.0000

Data Index: 968013 (The Pile)

Max Activating Token Index: 607

Text #7

Max Range: 3.6634. Min Range: -3.6634

Max Act: 3.0023. Min Act: -0.0000

Data Index: 1429224 (The Pile)

Max Activating Token Index: 141

Text #8

Max Range: 3.6634. Min Range: -3.6634

Max Act: 3.0997. Min Act: -0.0000

Data Index: 1379903 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 3.6634. Min Range: -3.6634

Max Act: 2.9456. Min Act: -0.0000

Data Index: 1899328 (The Pile)

Max Activating Token Index: 749

Text #10

Max Range: 3.6634. Min Range: -3.6634

Max Act: 2.7976. Min Act: -0.0000

Data Index: 1029421 (The Pile)

Max Activating Token Index: 751

Text #11

Max Range: 3.6634. Min Range: -3.6634

Max Act: 2.9333. Min Act: -0.0000

Data Index: 1570597 (The Pile)

Max Activating Token Index: 247

Text #12

Max Range: 3.6634. Min Range: -3.6634

Max Act: 2.9153. Min Act: -0.0000

Data Index: 480572 (The Pile)

Max Activating Token Index: 642

Text #13

Max Range: 3.6634. Min Range: -3.6634

Max Act: 2.9072. Min Act: -0.0000

Data Index: 311456 (The Pile)

Max Activating Token Index: 465

Text #14

Max Range: 3.6634. Min Range: -3.6634

Max Act: 2.8801. Min Act: -0.0000

Data Index: 1777026 (The Pile)

Max Activating Token Index: 546

Text #15

Max Range: 3.6634. Min Range: -3.6634

Max Act: 3.0226. Min Act: -0.0000

Data Index: 1052484 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 3.6634. Min Range: -3.6634

Max Act: 2.8440. Min Act: -0.0000

Data Index: 1638714 (The Pile)

Max Activating Token Index: 968

Text #17

Max Range: 3.6634. Min Range: -3.6634

Max Act: 2.4081. Min Act: -0.0000

Data Index: 591856 (The Pile)

Max Activating Token Index: 885

Text #18

Max Range: 3.6634. Min Range: -3.6634

Max Act: 2.9164. Min Act: -0.0000

Data Index: 1758350 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 3.6634. Min Range: -3.6634

Max Act: 2.5811. Min Act: -0.0000

Data Index: 385359 (The Pile)

Max Activating Token Index: 260