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

Dataset: The Pile

Neuron 4644 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0687. Min Act: -0.0000

Data Index: 363655 (The Pile)

Max Activating Token Index: 3

Text #1

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 380347 (The Pile)

Max Activating Token Index: 1

Text #2

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 117581 (The Pile)

Max Activating Token Index: 1

Text #3

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 340881 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 436878 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 535846 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 185235 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 158108 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 541678 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 483092 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 258299 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 189225 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 489095 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 36305 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: 0.0000

Data Index: 578440 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 547746 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 471585 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 313019 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 587544 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0670. Min Act: -0.0000

Data Index: 170302 (The Pile)

Max Activating Token Index: 1