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

Dataset: The Pile

Neuron 3974 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: 1.4941. Min Range: -1.4941

Max Act: 1.4941. Min Act: -0.0000

Data Index: 660898 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 1.4941. Min Range: -1.4941

Max Act: 1.2431. Min Act: -0.0000

Data Index: 1384818 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 1.4941. Min Range: -1.4941

Max Act: 1.1025. Min Act: -0.0000

Data Index: 1036118 (The Pile)

Max Activating Token Index: 735

Text #3

Max Range: 1.4941. Min Range: -1.4941

Max Act: 1.1987. Min Act: -0.0000

Data Index: 1363819 (The Pile)

Max Activating Token Index: 696

Text #4

Max Range: 1.4941. Min Range: -1.4941

Max Act: 1.1904. Min Act: -0.0000

Data Index: 1117471 (The Pile)

Max Activating Token Index: 246

Text #5

Max Range: 1.4941. Min Range: -1.4941

Max Act: 1.1538. Min Act: -0.0000

Data Index: 155009 (The Pile)

Max Activating Token Index: 445

Text #6

Max Range: 1.4941. Min Range: -1.4941

Max Act: 1.0856. Min Act: -0.0000

Data Index: 1667663 (The Pile)

Max Activating Token Index: 125

Text #7

Max Range: 1.4941. Min Range: -1.4941

Max Act: 1.1215. Min Act: -0.0000

Data Index: 1480949 (The Pile)

Max Activating Token Index: 370

Text #8

Max Range: 1.4941. Min Range: -1.4941

Max Act: 1.1094. Min Act: -0.0000

Data Index: 1405637 (The Pile)

Max Activating Token Index: 573

Text #9

Max Range: 1.4941. Min Range: -1.4941

Max Act: 1.0931. Min Act: -0.0000

Data Index: 1518872 (The Pile)

Max Activating Token Index: 83

Text #10

Max Range: 1.4941. Min Range: -1.4941

Max Act: 1.0869. Min Act: -0.0000

Data Index: 1107310 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 1.4941. Min Range: -1.4941

Max Act: 1.0456. Min Act: -0.0000

Data Index: 1099096 (The Pile)

Max Activating Token Index: 697

Text #12

Max Range: 1.4941. Min Range: -1.4941

Max Act: 1.0587. Min Act: -0.0000

Data Index: 452456 (The Pile)

Max Activating Token Index: 867

Text #13

Max Range: 1.4941. Min Range: -1.4941

Max Act: 1.0342. Min Act: -0.0000

Data Index: 1548148 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 1.4941. Min Range: -1.4941

Max Act: 1.0223. Min Act: -0.0000

Data Index: 603601 (The Pile)

Max Activating Token Index: 554

Text #15

Max Range: 1.4941. Min Range: -1.4941

Max Act: 0.9159. Min Act: -0.0000

Data Index: 1816638 (The Pile)

Max Activating Token Index: 693

Text #16

Max Range: 1.4941. Min Range: -1.4941

Max Act: 1.0290. Min Act: -0.0000

Data Index: 347465 (The Pile)

Max Activating Token Index: 582

Text #17

Max Range: 1.4941. Min Range: -1.4941

Max Act: 0.9585. Min Act: -0.0000

Data Index: 1456599 (The Pile)

Max Activating Token Index: 506

Text #18

Max Range: 1.4941. Min Range: -1.4941

Max Act: 0.9708. Min Act: -0.0000

Data Index: 234814 (The Pile)

Max Activating Token Index: 409

Text #19

Max Range: 1.4941. Min Range: -1.4941

Max Act: 0.9791. Min Act: -0.0000

Data Index: 130948 (The Pile)

Max Activating Token Index: 957