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

Dataset: The Pile

Neuron 534 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: 0.1161. Min Range: -0.1161

Max Act: 0.1161. Min Act: 0.0000

Data Index: 438269 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1088. Min Act: 0.0000

Data Index: 1104795 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1057. Min Act: 0.0000

Data Index: 1927309 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.1002. Min Act: 0.0000

Data Index: 1655539 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0994. Min Act: 0.0000

Data Index: 666266 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0966. Min Act: 0.0000

Data Index: 591558 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0953. Min Act: 0.0000

Data Index: 1042743 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0949. Min Act: 0.0000

Data Index: 492437 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0938. Min Act: 0.0000

Data Index: 1532930 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0930. Min Act: 0.0000

Data Index: 433219 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0925. Min Act: 0.0000

Data Index: 626873 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0923. Min Act: 0.0000

Data Index: 356896 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0921. Min Act: 0.0000

Data Index: 1465272 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0916. Min Act: 0.0000

Data Index: 59370 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0908. Min Act: 0.0000

Data Index: 1563350 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0934. Min Act: 0.0000

Data Index: 300459 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0898. Min Act: 0.0000

Data Index: 707726 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0901. Min Act: 0.0000

Data Index: 612213 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0897. Min Act: 0.0000

Data Index: 1070090 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1161. Min Range: -0.1161

Max Act: 0.0899. Min Act: 0.0000

Data Index: 323616 (The Pile)

Max Activating Token Index: 1023