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

Dataset: The Pile

Neuron 4842 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.9512. Min Act: -0.0000

Data Index: 614445 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.5403. Min Act: -0.0000

Data Index: 1529599 (The Pile)

Max Activating Token Index: 113

Text #2

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.6253. Min Act: -0.0000

Data Index: 32786 (The Pile)

Max Activating Token Index: 374

Text #3

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.7386. Min Act: -0.0000

Data Index: 1183639 (The Pile)

Max Activating Token Index: 625

Text #4

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.5107. Min Act: -0.0000

Data Index: 612879 (The Pile)

Max Activating Token Index: 471

Text #5

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.3322. Min Act: -0.0000

Data Index: 414190 (The Pile)

Max Activating Token Index: 947

Text #6

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.5094. Min Act: -0.0000

Data Index: 604619 (The Pile)

Max Activating Token Index: 393

Text #7

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.4185. Min Act: -0.0000

Data Index: 1570964 (The Pile)

Max Activating Token Index: 881

Text #8

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.6912. Min Act: -0.0000

Data Index: 1582279 (The Pile)

Max Activating Token Index: 158

Text #9

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.5754. Min Act: -0.0000

Data Index: 1157544 (The Pile)

Max Activating Token Index: 454

Text #10

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.3955. Min Act: -0.0000

Data Index: 1235919 (The Pile)

Max Activating Token Index: 744

Text #11

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.4749. Min Act: -0.0000

Data Index: 1390883 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.6146. Min Act: -0.0000

Data Index: 1748618 (The Pile)

Max Activating Token Index: 945

Text #13

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.3820. Min Act: -0.0000

Data Index: 1610060 (The Pile)

Max Activating Token Index: 536

Text #14

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.3664. Min Act: -0.0000

Data Index: 171867 (The Pile)

Max Activating Token Index: 850

Text #15

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.4331. Min Act: -0.0000

Data Index: 743281 (The Pile)

Max Activating Token Index: 769

Text #16

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.2893. Min Act: -0.0000

Data Index: 289480 (The Pile)

Max Activating Token Index: 59

Text #17

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.8198. Min Act: -0.0000

Data Index: 1610541 (The Pile)

Max Activating Token Index: 17

Text #18

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.3592. Min Act: -0.0000

Data Index: 13002 (The Pile)

Max Activating Token Index: 214

Text #19

Max Range: 1.9512. Min Range: -1.9512

Max Act: 1.7193. Min Act: -0.0000

Data Index: 1579738 (The Pile)

Max Activating Token Index: 34