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

Dataset: The Pile

Neuron 1739 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.7418. Min Act: -0.0000

Data Index: 510050 (The Pile)

Max Activating Token Index: 418

Text #1

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.8126. Min Act: -0.0000

Data Index: 509053 (The Pile)

Max Activating Token Index: 737

Text #2

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.3457. Min Act: -0.0000

Data Index: 1895044 (The Pile)

Max Activating Token Index: 979

Text #3

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.4915. Min Act: -0.0000

Data Index: 825249 (The Pile)

Max Activating Token Index: 783

Text #4

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.4410. Min Act: -0.0000

Data Index: 1463976 (The Pile)

Max Activating Token Index: 493

Text #5

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.5882. Min Act: -0.0000

Data Index: 217156 (The Pile)

Max Activating Token Index: 420

Text #6

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.0227. Min Act: -0.0000

Data Index: 1132320 (The Pile)

Max Activating Token Index: 759

Text #7

Max Range: 5.8126. Min Range: -5.8126

Max Act: 4.8389. Min Act: -0.0000

Data Index: 1884950 (The Pile)

Max Activating Token Index: 195

Text #8

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.1858. Min Act: -0.0000

Data Index: 1563758 (The Pile)

Max Activating Token Index: 155

Text #9

Max Range: 5.8126. Min Range: -5.8126

Max Act: 4.8945. Min Act: -0.0000

Data Index: 1383897 (The Pile)

Max Activating Token Index: 473

Text #10

Max Range: 5.8126. Min Range: -5.8126

Max Act: 4.9082. Min Act: -0.0000

Data Index: 397521 (The Pile)

Max Activating Token Index: 439

Text #11

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.0543. Min Act: -0.0000

Data Index: 1376219 (The Pile)

Max Activating Token Index: 163

Text #12

Max Range: 5.8126. Min Range: -5.8126

Max Act: 4.2091. Min Act: -0.0000

Data Index: 137039 (The Pile)

Max Activating Token Index: 931

Text #13

Max Range: 5.8126. Min Range: -5.8126

Max Act: 4.6730. Min Act: -0.0000

Data Index: 510675 (The Pile)

Max Activating Token Index: 872

Text #14

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.3649. Min Act: -0.0000

Data Index: 735685 (The Pile)

Max Activating Token Index: 772

Text #15

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.0128. Min Act: -0.0000

Data Index: 508633 (The Pile)

Max Activating Token Index: 788

Text #16

Max Range: 5.8126. Min Range: -5.8126

Max Act: 4.9816. Min Act: -0.0000

Data Index: 148227 (The Pile)

Max Activating Token Index: 366

Text #17

Max Range: 5.8126. Min Range: -5.8126

Max Act: 4.8462. Min Act: -0.0000

Data Index: 1027994 (The Pile)

Max Activating Token Index: 854

Text #18

Max Range: 5.8126. Min Range: -5.8126

Max Act: 4.7613. Min Act: -0.0000

Data Index: 143888 (The Pile)

Max Activating Token Index: 389

Text #19

Max Range: 5.8126. Min Range: -5.8126

Max Act: 5.1331. Min Act: -0.0000

Data Index: 594516 (The Pile)

Max Activating Token Index: 267