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

Dataset: The Pile

Neuron 2563 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: 3.7155. Min Range: -3.7155

Max Act: 3.7142. Min Act: -0.0000

Data Index: 1720404 (The Pile)

Max Activating Token Index: 549

Text #1

Max Range: 3.7155. Min Range: -3.7155

Max Act: 3.7142. Min Act: -0.0000

Data Index: 412490 (The Pile)

Max Activating Token Index: 360

Text #2

Max Range: 3.7155. Min Range: -3.7155

Max Act: 3.4728. Min Act: -0.0000

Data Index: 559934 (The Pile)

Max Activating Token Index: 722

Text #3

Max Range: 3.7155. Min Range: -3.7155

Max Act: 3.4384. Min Act: -0.0000

Data Index: 1834136 (The Pile)

Max Activating Token Index: 758

Text #4

Max Range: 3.7155. Min Range: -3.7155

Max Act: 3.5100. Min Act: -0.0000

Data Index: 1288635 (The Pile)

Max Activating Token Index: 456

Text #5

Max Range: 3.7155. Min Range: -3.7155

Max Act: 3.7155. Min Act: -0.0000

Data Index: 1217686 (The Pile)

Max Activating Token Index: 598

Text #6

Max Range: 3.7155. Min Range: -3.7155

Max Act: 3.3822. Min Act: -0.0000

Data Index: 657798 (The Pile)

Max Activating Token Index: 254

Text #7

Max Range: 3.7155. Min Range: -3.7155

Max Act: 3.1655. Min Act: -0.0000

Data Index: 1219699 (The Pile)

Max Activating Token Index: 606

Text #8

Max Range: 3.7155. Min Range: -3.7155

Max Act: 3.1562. Min Act: -0.0000

Data Index: 29910 (The Pile)

Max Activating Token Index: 799

Text #9

Max Range: 3.7155. Min Range: -3.7155

Max Act: 3.4483. Min Act: -0.0000

Data Index: 1208985 (The Pile)

Max Activating Token Index: 304

Text #10

Max Range: 3.7155. Min Range: -3.7155

Max Act: 3.2165. Min Act: -0.0000

Data Index: 1081695 (The Pile)

Max Activating Token Index: 355

Text #11

Max Range: 3.7155. Min Range: -3.7155

Max Act: 3.0674. Min Act: -0.0000

Data Index: 1262680 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 3.7155. Min Range: -3.7155

Max Act: 2.9724. Min Act: -0.0000

Data Index: 1764526 (The Pile)

Max Activating Token Index: 82

Text #13

Max Range: 3.7155. Min Range: -3.7155

Max Act: 3.0814. Min Act: -0.0000

Data Index: 534828 (The Pile)

Max Activating Token Index: 400

Text #14

Max Range: 3.7155. Min Range: -3.7155

Max Act: 3.0593. Min Act: -0.0000

Data Index: 1918065 (The Pile)

Max Activating Token Index: 867

Text #15

Max Range: 3.7155. Min Range: -3.7155

Max Act: 3.0217. Min Act: -0.0000

Data Index: 200527 (The Pile)

Max Activating Token Index: 648

Text #16

Max Range: 3.7155. Min Range: -3.7155

Max Act: 3.0058. Min Act: -0.0000

Data Index: 154877 (The Pile)

Max Activating Token Index: 567

Text #17

Max Range: 3.7155. Min Range: -3.7155

Max Act: 2.8643. Min Act: -0.0000

Data Index: 1956401 (The Pile)

Max Activating Token Index: 557

Text #18

Max Range: 3.7155. Min Range: -3.7155

Max Act: 2.8728. Min Act: -0.0000

Data Index: 285407 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 3.7155. Min Range: -3.7155

Max Act: 2.8524. Min Act: -0.0000

Data Index: 415589 (The Pile)

Max Activating Token Index: 670