Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 223 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1721118 (The Pile)

Max Activating Token Index: 280

Text #1

Max Range: 1.0644. Min Range: -1.0644

Max Act: 1.0644. Min Act: -0.0000

Data Index: 121295 (The Pile)

Max Activating Token Index: 980

Text #2

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.8779. Min Act: -0.0000

Data Index: 202382 (The Pile)

Max Activating Token Index: 954

Text #3

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.8283. Min Act: -0.0000

Data Index: 1327552 (The Pile)

Max Activating Token Index: 993

Text #4

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.8690. Min Act: -0.0000

Data Index: 1687781 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.8110. Min Act: -0.0000

Data Index: 469010 (The Pile)

Max Activating Token Index: 907

Text #6

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.7772. Min Act: -0.0000

Data Index: 7897 (The Pile)

Max Activating Token Index: 899

Text #7

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.8091. Min Act: -0.0000

Data Index: 583333 (The Pile)

Max Activating Token Index: 797

Text #8

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.8226. Min Act: -0.0000

Data Index: 257171 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.8131. Min Act: -0.0000

Data Index: 1039733 (The Pile)

Max Activating Token Index: 722

Text #10

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.7986. Min Act: -0.0000

Data Index: 712873 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.7637. Min Act: -0.0000

Data Index: 1378598 (The Pile)

Max Activating Token Index: 287

Text #12

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.7605. Min Act: -0.0000

Data Index: 380702 (The Pile)

Max Activating Token Index: 208

Text #13

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1593974 (The Pile)

Max Activating Token Index: 808

Text #14

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.7712. Min Act: -0.0000

Data Index: 513277 (The Pile)

Max Activating Token Index: 98

Text #15

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1411388 (The Pile)

Max Activating Token Index: 696

Text #16

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.7825. Min Act: -0.0000

Data Index: 300 (The Pile)

Max Activating Token Index: 861

Text #17

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.8148. Min Act: -0.0000

Data Index: 106663 (The Pile)

Max Activating Token Index: 889

Text #18

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1107947 (The Pile)

Max Activating Token Index: 807

Text #19

Max Range: 1.0644. Min Range: -1.0644

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1007639 (The Pile)

Max Activating Token Index: 440