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

Dataset: The Pile

Neuron 3604 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7105. Min Range: -5.7105

Max Act: 5.7105. Min Act: -0.0000

Data Index: 1343273 (The Pile)

Max Activating Token Index: 574

Text #1

Max Range: 5.7105. Min Range: -5.7105

Max Act: 4.6043. Min Act: -0.0000

Data Index: 905752 (The Pile)

Max Activating Token Index: 251

Text #2

Max Range: 5.7105. Min Range: -5.7105

Max Act: 5.0626. Min Act: -0.0000

Data Index: 1285506 (The Pile)

Max Activating Token Index: 706

Text #3

Max Range: 5.7105. Min Range: -5.7105

Max Act: 4.5213. Min Act: -0.0000

Data Index: 502289 (The Pile)

Max Activating Token Index: 795

Text #4

Max Range: 5.7105. Min Range: -5.7105

Max Act: 4.5152. Min Act: -0.0000

Data Index: 1993208 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 5.7105. Min Range: -5.7105

Max Act: 4.0922. Min Act: -0.0000

Data Index: 1542786 (The Pile)

Max Activating Token Index: 795

Text #6

Max Range: 5.7105. Min Range: -5.7105

Max Act: 3.9584. Min Act: -0.0000

Data Index: 212784 (The Pile)

Max Activating Token Index: 133

Text #7

Max Range: 5.7105. Min Range: -5.7105

Max Act: 3.5467. Min Act: -0.0000

Data Index: 1471936 (The Pile)

Max Activating Token Index: 352

Text #8

Max Range: 5.7105. Min Range: -5.7105

Max Act: 3.1937. Min Act: -0.0000

Data Index: 651691 (The Pile)

Max Activating Token Index: 691

Text #9

Max Range: 5.7105. Min Range: -5.7105

Max Act: 3.2305. Min Act: -0.0000

Data Index: 715690 (The Pile)

Max Activating Token Index: 349

Text #10

Max Range: 5.7105. Min Range: -5.7105

Max Act: 3.0090. Min Act: -0.0000

Data Index: 1835735 (The Pile)

Max Activating Token Index: 839

Text #11

Max Range: 5.7105. Min Range: -5.7105

Max Act: 3.1095. Min Act: -0.0000

Data Index: 693479 (The Pile)

Max Activating Token Index: 550

Text #12

Max Range: 5.7105. Min Range: -5.7105

Max Act: 2.9403. Min Act: -0.0000

Data Index: 832060 (The Pile)

Max Activating Token Index: 468

Text #13

Max Range: 5.7105. Min Range: -5.7105

Max Act: 2.9009. Min Act: -0.0000

Data Index: 218547 (The Pile)

Max Activating Token Index: 287

Text #14

Max Range: 5.7105. Min Range: -5.7105

Max Act: 2.6715. Min Act: -0.0000

Data Index: 1932748 (The Pile)

Max Activating Token Index: 532

Text #15

Max Range: 5.7105. Min Range: -5.7105

Max Act: 3.0199. Min Act: -0.0000

Data Index: 637960 (The Pile)

Max Activating Token Index: 598

Text #16

Max Range: 5.7105. Min Range: -5.7105

Max Act: 2.7540. Min Act: -0.0000

Data Index: 543267 (The Pile)

Max Activating Token Index: 532

Text #17

Max Range: 5.7105. Min Range: -5.7105

Max Act: 2.8359. Min Act: -0.0000

Data Index: 106166 (The Pile)

Max Activating Token Index: 426

Text #18

Max Range: 5.7105. Min Range: -5.7105

Max Act: 2.8684. Min Act: -0.0000

Data Index: 750706 (The Pile)

Max Activating Token Index: 422

Text #19

Max Range: 5.7105. Min Range: -5.7105

Max Act: 2.5396. Min Act: -0.0000

Data Index: 92382 (The Pile)

Max Activating Token Index: 387