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

Dataset: The Pile

Neuron 977 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: 3.7869. Min Range: -3.7869

Max Act: 3.7869. Min Act: -0.0000

Data Index: 690247 (The Pile)

Max Activating Token Index: 574

Text #1

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.4954. Min Act: -0.0000

Data Index: 498665 (The Pile)

Max Activating Token Index: 282

Text #2

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.4370. Min Act: -0.0000

Data Index: 298203 (The Pile)

Max Activating Token Index: 587

Text #3

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.4820. Min Act: -0.0000

Data Index: 377898 (The Pile)

Max Activating Token Index: 874

Text #4

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.2205. Min Act: -0.0000

Data Index: 1304487 (The Pile)

Max Activating Token Index: 428

Text #5

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.5171. Min Act: -0.0000

Data Index: 1967881 (The Pile)

Max Activating Token Index: 932

Text #6

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.6516. Min Act: -0.0000

Data Index: 1928792 (The Pile)

Max Activating Token Index: 975

Text #7

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.1920. Min Act: -0.0000

Data Index: 1475393 (The Pile)

Max Activating Token Index: 501

Text #8

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.1699. Min Act: -0.0000

Data Index: 1090392 (The Pile)

Max Activating Token Index: 791

Text #9

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.2733. Min Act: -0.0000

Data Index: 1479444 (The Pile)

Max Activating Token Index: 331

Text #10

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.2733. Min Act: -0.0000

Data Index: 1131288 (The Pile)

Max Activating Token Index: 465

Text #11

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.4120. Min Act: -0.0000

Data Index: 846754 (The Pile)

Max Activating Token Index: 811

Text #12

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.4290. Min Act: -0.0000

Data Index: 406062 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 3.7869. Min Range: -3.7869

Max Act: 2.9735. Min Act: -0.0000

Data Index: 526305 (The Pile)

Max Activating Token Index: 991

Text #14

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.1076. Min Act: -0.0000

Data Index: 1855722 (The Pile)

Max Activating Token Index: 374

Text #15

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.4040. Min Act: -0.0000

Data Index: 719405 (The Pile)

Max Activating Token Index: 102

Text #16

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.1112. Min Act: -0.0000

Data Index: 176231 (The Pile)

Max Activating Token Index: 342

Text #17

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.1027. Min Act: -0.0000

Data Index: 1938944 (The Pile)

Max Activating Token Index: 631

Text #18

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.3940. Min Act: -0.0000

Data Index: 858773 (The Pile)

Max Activating Token Index: 277

Text #19

Max Range: 3.7869. Min Range: -3.7869

Max Act: 3.0698. Min Act: -0.0000

Data Index: 908950 (The Pile)

Max Activating Token Index: 763