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

Dataset: The Pile

Neuron 1980 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.2653. Min Act: -0.0000

Data Index: 305884 (The Pile)

Max Activating Token Index: 32

Text #1

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1577473 (The Pile)

Max Activating Token Index: 699

Text #2

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0093. Min Act: -0.0000

Data Index: 335617 (The Pile)

Max Activating Token Index: 789

Text #3

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.1175. Min Act: -0.0000

Data Index: 640469 (The Pile)

Max Activating Token Index: 514

Text #4

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0625. Min Act: -0.0000

Data Index: 509171 (The Pile)

Max Activating Token Index: 420

Text #5

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.1142. Min Act: -0.0000

Data Index: 1592195 (The Pile)

Max Activating Token Index: 269

Text #6

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.1300. Min Act: -0.0000

Data Index: 1400589 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1796418 (The Pile)

Max Activating Token Index: 23

Text #8

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0036. Min Act: -0.0000

Data Index: 1883466 (The Pile)

Max Activating Token Index: 841

Text #9

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9905. Min Act: -0.0000

Data Index: 1120287 (The Pile)

Max Activating Token Index: 320

Text #10

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9813. Min Act: -0.0000

Data Index: 1799266 (The Pile)

Max Activating Token Index: 42

Text #11

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.8601. Min Act: -0.0000

Data Index: 175786 (The Pile)

Max Activating Token Index: 151

Text #12

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9595. Min Act: -0.0000

Data Index: 865682 (The Pile)

Max Activating Token Index: 566

Text #13

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9551. Min Act: -0.0000

Data Index: 1891068 (The Pile)

Max Activating Token Index: 595

Text #14

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0905. Min Act: -0.0000

Data Index: 1562946 (The Pile)

Max Activating Token Index: 68

Text #15

Max Range: 1.2653. Min Range: -1.2653

Max Act: 1.0092. Min Act: -0.0000

Data Index: 179240 (The Pile)

Max Activating Token Index: 65

Text #16

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9419. Min Act: -0.0000

Data Index: 673337 (The Pile)

Max Activating Token Index: 190

Text #17

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.8885. Min Act: -0.0000

Data Index: 492066 (The Pile)

Max Activating Token Index: 903

Text #18

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.9338. Min Act: -0.0000

Data Index: 782136 (The Pile)

Max Activating Token Index: 236

Text #19

Max Range: 1.2653. Min Range: -1.2653

Max Act: 0.8998. Min Act: -0.0000

Data Index: 1116680 (The Pile)

Max Activating Token Index: 925