Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2884 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.5225. Min Act: 0.0000

Data Index: 1588142 (The Pile)

Max Activating Token Index: 258

Text #1

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1299782 (The Pile)

Max Activating Token Index: 602

Text #2

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.2952. Min Act: -0.0001

Data Index: 1479449 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.3029. Min Act: -0.0000

Data Index: 615180 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.2855. Min Act: -0.0000

Data Index: 420719 (The Pile)

Max Activating Token Index: 906

Text #5

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.2947. Min Act: -0.0001

Data Index: 372810 (The Pile)

Max Activating Token Index: 534

Text #6

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.2928. Min Act: 0.0000

Data Index: 1982812 (The Pile)

Max Activating Token Index: 335

Text #7

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1418962 (The Pile)

Max Activating Token Index: 877

Text #8

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.2800. Min Act: -0.0000

Data Index: 620530 (The Pile)

Max Activating Token Index: 909

Text #9

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1226921 (The Pile)

Max Activating Token Index: 657

Text #10

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1775182 (The Pile)

Max Activating Token Index: 391

Text #11

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.2951. Min Act: -0.0000

Data Index: 315002 (The Pile)

Max Activating Token Index: 952

Text #12

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.2859. Min Act: -0.0001

Data Index: 448256 (The Pile)

Max Activating Token Index: 213

Text #13

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1696646 (The Pile)

Max Activating Token Index: 918

Text #14

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.2698. Min Act: -0.0000

Data Index: 160423 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.2681. Min Act: -0.0001

Data Index: 1036938 (The Pile)

Max Activating Token Index: 678

Text #16

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.2787. Min Act: 0.0000

Data Index: 1545366 (The Pile)

Max Activating Token Index: 244

Text #17

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.2728. Min Act: -0.0000

Data Index: 685366 (The Pile)

Max Activating Token Index: 744

Text #18

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1748988 (The Pile)

Max Activating Token Index: 700

Text #19

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.2708. Min Act: -0.0000

Data Index: 1665491 (The Pile)

Max Activating Token Index: 548