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

Dataset: The Pile

Neuron 1874 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: 1.0440. Min Range: -1.0440

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1602831 (The Pile)

Max Activating Token Index: 249

Text #1

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.9045. Min Act: -0.0000

Data Index: 1299734 (The Pile)

Max Activating Token Index: 958

Text #2

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1556185 (The Pile)

Max Activating Token Index: 666

Text #3

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8356. Min Act: -0.0000

Data Index: 77471 (The Pile)

Max Activating Token Index: 439

Text #4

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7703. Min Act: -0.0000

Data Index: 1053551 (The Pile)

Max Activating Token Index: 489

Text #5

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1593339 (The Pile)

Max Activating Token Index: 469

Text #6

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7672. Min Act: -0.0000

Data Index: 768362 (The Pile)

Max Activating Token Index: 619

Text #7

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1095904 (The Pile)

Max Activating Token Index: 188

Text #8

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6950. Min Act: -0.0000

Data Index: 158460 (The Pile)

Max Activating Token Index: 277

Text #9

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7969. Min Act: -0.0000

Data Index: 622646 (The Pile)

Max Activating Token Index: 334

Text #10

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1050243 (The Pile)

Max Activating Token Index: 492

Text #11

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7355. Min Act: -0.0000

Data Index: 1129767 (The Pile)

Max Activating Token Index: 740

Text #12

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6648. Min Act: -0.0000

Data Index: 1943478 (The Pile)

Max Activating Token Index: 1019

Text #13

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6176. Min Act: -0.0000

Data Index: 474011 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6563. Min Act: -0.0000

Data Index: 223428 (The Pile)

Max Activating Token Index: 398

Text #15

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1588027 (The Pile)

Max Activating Token Index: 944

Text #16

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1560980 (The Pile)

Max Activating Token Index: 127

Text #17

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6674. Min Act: -0.0000

Data Index: 277648 (The Pile)

Max Activating Token Index: 534

Text #18

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6500. Min Act: -0.0000

Data Index: 1956659 (The Pile)

Max Activating Token Index: 806

Text #19

Max Range: 1.0440. Min Range: -1.0440

Max Act: 0.6593. Min Act: -0.0000

Data Index: 952934 (The Pile)

Max Activating Token Index: 153