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

Dataset: The Pile

Neuron 3555 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: 0.4246. Min Range: -0.4246

Max Act: 0.4093. Min Act: -0.0000

Data Index: 1992592 (The Pile)

Max Activating Token Index: 81

Text #1

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3717. Min Act: -0.0000

Data Index: 612075 (The Pile)

Max Activating Token Index: 881

Text #2

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3758. Min Act: -0.0000

Data Index: 762180 (The Pile)

Max Activating Token Index: 52

Text #3

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3864. Min Act: -0.0000

Data Index: 458913 (The Pile)

Max Activating Token Index: 169

Text #4

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.4246. Min Act: -0.0000

Data Index: 1054703 (The Pile)

Max Activating Token Index: 255

Text #5

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1739034 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3306. Min Act: -0.0000

Data Index: 966893 (The Pile)

Max Activating Token Index: 527

Text #7

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3431. Min Act: -0.0000

Data Index: 1751076 (The Pile)

Max Activating Token Index: 43

Text #8

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1773582 (The Pile)

Max Activating Token Index: 985

Text #9

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1123114 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1978621 (The Pile)

Max Activating Token Index: 374

Text #11

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3243. Min Act: -0.0000

Data Index: 466653 (The Pile)

Max Activating Token Index: 112

Text #12

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3215. Min Act: -0.0000

Data Index: 1456895 (The Pile)

Max Activating Token Index: 790

Text #13

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1446717 (The Pile)

Max Activating Token Index: 553

Text #14

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2961. Min Act: -0.0000

Data Index: 60263 (The Pile)

Max Activating Token Index: 732

Text #15

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3124. Min Act: -0.0000

Data Index: 1949648 (The Pile)

Max Activating Token Index: 879

Text #16

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3081. Min Act: -0.0000

Data Index: 1009958 (The Pile)

Max Activating Token Index: 673

Text #17

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1113243 (The Pile)

Max Activating Token Index: 919

Text #18

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2857. Min Act: -0.0000

Data Index: 786357 (The Pile)

Max Activating Token Index: 517

Text #19

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2938. Min Act: -0.0000

Data Index: 628068 (The Pile)

Max Activating Token Index: 196