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

Dataset: The Pile

Neuron 2050 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: 4.1601. Min Range: -4.1601

Max Act: 4.1601. Min Act: -0.0000

Data Index: 671938 (The Pile)

Max Activating Token Index: 48

Text #1

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.9680. Min Act: -0.0000

Data Index: 1108097 (The Pile)

Max Activating Token Index: 593

Text #2

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.9670. Min Act: -0.0000

Data Index: 1268040 (The Pile)

Max Activating Token Index: 746

Text #3

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.5904. Min Act: -0.0000

Data Index: 1218249 (The Pile)

Max Activating Token Index: 572

Text #4

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.7017. Min Act: -0.0000

Data Index: 1029298 (The Pile)

Max Activating Token Index: 943

Text #5

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.4790. Min Act: -0.0000

Data Index: 1092971 (The Pile)

Max Activating Token Index: 484

Text #6

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.4586. Min Act: -0.0000

Data Index: 829595 (The Pile)

Max Activating Token Index: 606

Text #7

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.5911. Min Act: -0.0000

Data Index: 1424045 (The Pile)

Max Activating Token Index: 372

Text #8

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.5396. Min Act: -0.0000

Data Index: 287862 (The Pile)

Max Activating Token Index: 361

Text #9

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.5192. Min Act: -0.0000

Data Index: 341495 (The Pile)

Max Activating Token Index: 739

Text #10

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.4484. Min Act: -0.0000

Data Index: 1219553 (The Pile)

Max Activating Token Index: 281

Text #11

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.4256. Min Act: -0.0000

Data Index: 11805 (The Pile)

Max Activating Token Index: 822

Text #12

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.3092. Min Act: -0.0000

Data Index: 1492836 (The Pile)

Max Activating Token Index: 323

Text #13

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.4109. Min Act: -0.0000

Data Index: 163598 (The Pile)

Max Activating Token Index: 385

Text #14

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.4557. Min Act: -0.0000

Data Index: 1472212 (The Pile)

Max Activating Token Index: 150

Text #15

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.2486. Min Act: -0.0000

Data Index: 1645212 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.4232. Min Act: -0.0000

Data Index: 621063 (The Pile)

Max Activating Token Index: 671

Text #17

Max Range: 4.1601. Min Range: -4.1601

Max Act: 2.9714. Min Act: -0.0000

Data Index: 1058693 (The Pile)

Max Activating Token Index: 131

Text #18

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.3565. Min Act: -0.0000

Data Index: 1497330 (The Pile)

Max Activating Token Index: 425

Text #19

Max Range: 4.1601. Min Range: -4.1601

Max Act: 3.0252. Min Act: -0.0000

Data Index: 567529 (The Pile)

Max Activating Token Index: 185