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

Dataset: The Pile

Neuron 2941 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.4730. Min Act: -0.0000

Data Index: 1191468 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.1618. Min Act: -0.0000

Data Index: 1338211 (The Pile)

Max Activating Token Index: 912

Text #2

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2385. Min Act: -0.0000

Data Index: 1363904 (The Pile)

Max Activating Token Index: 843

Text #3

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.1566. Min Act: -0.0000

Data Index: 130437 (The Pile)

Max Activating Token Index: 979

Text #4

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2680. Min Act: -0.0000

Data Index: 1526170 (The Pile)

Max Activating Token Index: 189

Text #5

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.1616. Min Act: -0.0000

Data Index: 873306 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2063. Min Act: -0.0000

Data Index: 272867 (The Pile)

Max Activating Token Index: 128

Text #7

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2016. Min Act: -0.0000

Data Index: 1056463 (The Pile)

Max Activating Token Index: 379

Text #8

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.3169. Min Act: -0.0000

Data Index: 483809 (The Pile)

Max Activating Token Index: 887

Text #9

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.1277. Min Act: -0.0000

Data Index: 148927 (The Pile)

Max Activating Token Index: 332

Text #10

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.1883. Min Act: -0.0000

Data Index: 1156950 (The Pile)

Max Activating Token Index: 976

Text #11

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0902. Min Act: -0.0000

Data Index: 1947703 (The Pile)

Max Activating Token Index: 1007

Text #12

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0937. Min Act: -0.0000

Data Index: 408786 (The Pile)

Max Activating Token Index: 973

Text #13

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.1154. Min Act: -0.0000

Data Index: 1959507 (The Pile)

Max Activating Token Index: 671

Text #14

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0148. Min Act: -0.0000

Data Index: 372865 (The Pile)

Max Activating Token Index: 899

Text #15

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0454. Min Act: -0.0000

Data Index: 1522263 (The Pile)

Max Activating Token Index: 797

Text #16

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0621. Min Act: -0.0000

Data Index: 1708872 (The Pile)

Max Activating Token Index: 460

Text #17

Max Range: 1.4730. Min Range: -1.4730

Max Act: 0.9936. Min Act: -0.0000

Data Index: 1910082 (The Pile)

Max Activating Token Index: 948

Text #18

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0466. Min Act: -0.0000

Data Index: 786931 (The Pile)

Max Activating Token Index: 993

Text #19

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0832. Min Act: -0.0000

Data Index: 33143 (The Pile)

Max Activating Token Index: 500