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

Dataset: The Pile

Neuron 2205 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: 3.2689. Min Range: -3.2689

Max Act: 3.1964. Min Act: -0.0000

Data Index: 996390 (The Pile)

Max Activating Token Index: 261

Text #1

Max Range: 3.2689. Min Range: -3.2689

Max Act: 3.2349. Min Act: -0.0000

Data Index: 1577946 (The Pile)

Max Activating Token Index: 204

Text #2

Max Range: 3.2689. Min Range: -3.2689

Max Act: 2.8172. Min Act: -0.0000

Data Index: 1560670 (The Pile)

Max Activating Token Index: 702

Text #3

Max Range: 3.2689. Min Range: -3.2689

Max Act: 3.2683. Min Act: -0.0000

Data Index: 1991867 (The Pile)

Max Activating Token Index: 697

Text #4

Max Range: 3.2689. Min Range: -3.2689

Max Act: 3.1082. Min Act: -0.0000

Data Index: 1882213 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 3.2689. Min Range: -3.2689

Max Act: 3.2689. Min Act: -0.0000

Data Index: 1963164 (The Pile)

Max Activating Token Index: 18

Text #6

Max Range: 3.2689. Min Range: -3.2689

Max Act: 3.0845. Min Act: -0.0000

Data Index: 522416 (The Pile)

Max Activating Token Index: 511

Text #7

Max Range: 3.2689. Min Range: -3.2689

Max Act: 3.0476. Min Act: -0.0000

Data Index: 473310 (The Pile)

Max Activating Token Index: 430

Text #8

Max Range: 3.2689. Min Range: -3.2689

Max Act: 3.0647. Min Act: -0.0000

Data Index: 555814 (The Pile)

Max Activating Token Index: 218

Text #9

Max Range: 3.2689. Min Range: -3.2689

Max Act: 3.0056. Min Act: -0.0000

Data Index: 161899 (The Pile)

Max Activating Token Index: 893

Text #10

Max Range: 3.2689. Min Range: -3.2689

Max Act: 3.0629. Min Act: -0.0000

Data Index: 806006 (The Pile)

Max Activating Token Index: 286

Text #11

Max Range: 3.2689. Min Range: -3.2689

Max Act: 3.0202. Min Act: -0.0000

Data Index: 402693 (The Pile)

Max Activating Token Index: 800

Text #12

Max Range: 3.2689. Min Range: -3.2689

Max Act: 3.0023. Min Act: -0.0000

Data Index: 1594127 (The Pile)

Max Activating Token Index: 344

Text #13

Max Range: 3.2689. Min Range: -3.2689

Max Act: 2.7404. Min Act: -0.0000

Data Index: 908001 (The Pile)

Max Activating Token Index: 590

Text #14

Max Range: 3.2689. Min Range: -3.2689

Max Act: 3.0119. Min Act: -0.0000

Data Index: 1133312 (The Pile)

Max Activating Token Index: 759

Text #15

Max Range: 3.2689. Min Range: -3.2689

Max Act: 2.7269. Min Act: -0.0000

Data Index: 744673 (The Pile)

Max Activating Token Index: 522

Text #16

Max Range: 3.2689. Min Range: -3.2689

Max Act: 3.0925. Min Act: -0.0000

Data Index: 509386 (The Pile)

Max Activating Token Index: 520

Text #17

Max Range: 3.2689. Min Range: -3.2689

Max Act: 2.9607. Min Act: -0.0000

Data Index: 727667 (The Pile)

Max Activating Token Index: 845

Text #18

Max Range: 3.2689. Min Range: -3.2689

Max Act: 2.8693. Min Act: -0.0000

Data Index: 1498486 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 3.2689. Min Range: -3.2689

Max Act: 2.8058. Min Act: -0.0000

Data Index: 1941402 (The Pile)

Max Activating Token Index: 511