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

Dataset: The Pile

Neuron 1124 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: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 267286 (The Pile)

Max Activating Token Index: 1

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 44521 (The Pile)

Max Activating Token Index: 1

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 295004 (The Pile)

Max Activating Token Index: 1

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 272064 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 34053 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: 0.0000

Data Index: 271663 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: 0.0000

Data Index: 52475 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 301181 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 125671 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 14214 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 72943 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 243774 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: 0.0000

Data Index: 111951 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 198367 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 58161 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 181803 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 297949 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 157605 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 152799 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0000

Data Index: 151688 (The Pile)

Max Activating Token Index: 1