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

Dataset: The Pile

Neuron 4696 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: 5.5715. Min Range: -5.5715

Max Act: 5.5715. Min Act: -0.0000

Data Index: 357530 (The Pile)

Max Activating Token Index: 770

Text #1

Max Range: 5.5715. Min Range: -5.5715

Max Act: 5.1838. Min Act: -0.0000

Data Index: 1287300 (The Pile)

Max Activating Token Index: 96

Text #2

Max Range: 5.5715. Min Range: -5.5715

Max Act: 5.1141. Min Act: -0.0000

Data Index: 1419538 (The Pile)

Max Activating Token Index: 677

Text #3

Max Range: 5.5715. Min Range: -5.5715

Max Act: 5.0981. Min Act: -0.0000

Data Index: 1866222 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 5.5715. Min Range: -5.5715

Max Act: 5.0913. Min Act: -0.0000

Data Index: 11387 (The Pile)

Max Activating Token Index: 601

Text #5

Max Range: 5.5715. Min Range: -5.5715

Max Act: 4.9435. Min Act: -0.0000

Data Index: 1725836 (The Pile)

Max Activating Token Index: 542

Text #6

Max Range: 5.5715. Min Range: -5.5715

Max Act: 4.9569. Min Act: -0.0000

Data Index: 406006 (The Pile)

Max Activating Token Index: 681

Text #7

Max Range: 5.5715. Min Range: -5.5715

Max Act: 4.7307. Min Act: -0.0000

Data Index: 701318 (The Pile)

Max Activating Token Index: 177

Text #8

Max Range: 5.5715. Min Range: -5.5715

Max Act: 4.8945. Min Act: -0.0000

Data Index: 984559 (The Pile)

Max Activating Token Index: 637

Text #9

Max Range: 5.5715. Min Range: -5.5715

Max Act: 4.8900. Min Act: -0.0000

Data Index: 1923882 (The Pile)

Max Activating Token Index: 952

Text #10

Max Range: 5.5715. Min Range: -5.5715

Max Act: 4.7464. Min Act: -0.0000

Data Index: 1719698 (The Pile)

Max Activating Token Index: 926

Text #11

Max Range: 5.5715. Min Range: -5.5715

Max Act: 5.2768. Min Act: -0.0000

Data Index: 45143 (The Pile)

Max Activating Token Index: 965

Text #12

Max Range: 5.5715. Min Range: -5.5715

Max Act: 4.7214. Min Act: -0.0000

Data Index: 1695229 (The Pile)

Max Activating Token Index: 300

Text #13

Max Range: 5.5715. Min Range: -5.5715

Max Act: 4.5083. Min Act: -0.0000

Data Index: 84239 (The Pile)

Max Activating Token Index: 86

Text #14

Max Range: 5.5715. Min Range: -5.5715

Max Act: 4.6511. Min Act: -0.0000

Data Index: 605166 (The Pile)

Max Activating Token Index: 1020

Text #15

Max Range: 5.5715. Min Range: -5.5715

Max Act: 4.5140. Min Act: -0.0000

Data Index: 1120958 (The Pile)

Max Activating Token Index: 774

Text #16

Max Range: 5.5715. Min Range: -5.5715

Max Act: 4.4667. Min Act: -0.0000

Data Index: 1255435 (The Pile)

Max Activating Token Index: 441

Text #17

Max Range: 5.5715. Min Range: -5.5715

Max Act: 4.6178. Min Act: -0.0000

Data Index: 586554 (The Pile)

Max Activating Token Index: 648

Text #18

Max Range: 5.5715. Min Range: -5.5715

Max Act: 4.8043. Min Act: -0.0000

Data Index: 611298 (The Pile)

Max Activating Token Index: 36

Text #19

Max Range: 5.5715. Min Range: -5.5715

Max Act: 4.6184. Min Act: -0.0000

Data Index: 349687 (The Pile)

Max Activating Token Index: 608