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

Dataset: The Pile

Neuron 1386 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.8374. Min Act: -0.0000

Data Index: 1597890 (The Pile)

Max Activating Token Index: 800

Text #1

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.7879. Min Act: -0.0000

Data Index: 1092575 (The Pile)

Max Activating Token Index: 602

Text #2

Max Range: 3.1912. Min Range: -3.1912

Max Act: 3.1912. Min Act: -0.0000

Data Index: 829456 (The Pile)

Max Activating Token Index: 471

Text #3

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.7151. Min Act: -0.0000

Data Index: 172655 (The Pile)

Max Activating Token Index: 647

Text #4

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.9456. Min Act: -0.0000

Data Index: 749882 (The Pile)

Max Activating Token Index: 532

Text #5

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.6056. Min Act: -0.0000

Data Index: 314740 (The Pile)

Max Activating Token Index: 462

Text #6

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.5902. Min Act: -0.0000

Data Index: 1543606 (The Pile)

Max Activating Token Index: 698

Text #7

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.2749. Min Act: -0.0000

Data Index: 1480095 (The Pile)

Max Activating Token Index: 262

Text #8

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.6447. Min Act: -0.0000

Data Index: 6734 (The Pile)

Max Activating Token Index: 447

Text #9

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.7591. Min Act: -0.0000

Data Index: 1455765 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.4749. Min Act: -0.0000

Data Index: 1309650 (The Pile)

Max Activating Token Index: 895

Text #11

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.5502. Min Act: -0.0000

Data Index: 421605 (The Pile)

Max Activating Token Index: 442

Text #12

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.4382. Min Act: -0.0000

Data Index: 274896 (The Pile)

Max Activating Token Index: 470

Text #13

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.5521. Min Act: -0.0000

Data Index: 827388 (The Pile)

Max Activating Token Index: 762

Text #14

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.6688. Min Act: -0.0000

Data Index: 289509 (The Pile)

Max Activating Token Index: 531

Text #15

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.5132. Min Act: -0.0000

Data Index: 1976306 (The Pile)

Max Activating Token Index: 559

Text #16

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.5594. Min Act: -0.0000

Data Index: 310773 (The Pile)

Max Activating Token Index: 799

Text #17

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.5314. Min Act: -0.0000

Data Index: 315592 (The Pile)

Max Activating Token Index: 360

Text #18

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.4111. Min Act: -0.0000

Data Index: 1289553 (The Pile)

Max Activating Token Index: 851

Text #19

Max Range: 3.1912. Min Range: -3.1912

Max Act: 2.4874. Min Act: -0.0000

Data Index: 1699734 (The Pile)

Max Activating Token Index: 268