Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 817 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 1.1744. Min Range: -1.1744

Max Act: 1.1561. Min Act: -0.0000

Data Index: 626700 (The Pile)

Max Activating Token Index: 881

Text #1

Max Range: 1.1744. Min Range: -1.1744

Max Act: 1.1744. Min Act: -0.0001

Data Index: 1416550 (The Pile)

Max Activating Token Index: 491

Text #2

Max Range: 1.1744. Min Range: -1.1744

Max Act: 1.1205. Min Act: -0.0000

Data Index: 1047584 (The Pile)

Max Activating Token Index: 997

Text #3

Max Range: 1.1744. Min Range: -1.1744

Max Act: 1.1161. Min Act: -0.0001

Data Index: 478677 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 1.1744. Min Range: -1.1744

Max Act: 1.0423. Min Act: -0.0000

Data Index: 1478332 (The Pile)

Max Activating Token Index: 1007

Text #5

Max Range: 1.1744. Min Range: -1.1744

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1318105 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 1.1744. Min Range: -1.1744

Max Act: 0.9909. Min Act: -0.0000

Data Index: 549214 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 1.1744. Min Range: -1.1744

Max Act: 0.9930. Min Act: -0.0001

Data Index: 1327234 (The Pile)

Max Activating Token Index: 564

Text #8

Max Range: 1.1744. Min Range: -1.1744

Max Act: 0.9880. Min Act: -0.0000

Data Index: 935457 (The Pile)

Max Activating Token Index: 639

Text #9

Max Range: 1.1744. Min Range: -1.1744

Max Act: 0.9560. Min Act: -0.0000

Data Index: 1453847 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 1.1744. Min Range: -1.1744

Max Act: 0.9880. Min Act: -0.0000

Data Index: 1650956 (The Pile)

Max Activating Token Index: 851

Text #11

Max Range: 1.1744. Min Range: -1.1744

Max Act: 0.9851. Min Act: -0.0001

Data Index: 1416285 (The Pile)

Max Activating Token Index: 461

Text #12

Max Range: 1.1744. Min Range: -1.1744

Max Act: 0.9464. Min Act: -0.0001

Data Index: 504845 (The Pile)

Max Activating Token Index: 737

Text #13

Max Range: 1.1744. Min Range: -1.1744

Max Act: 0.9785. Min Act: -0.0001

Data Index: 1714608 (The Pile)

Max Activating Token Index: 62

Text #14

Max Range: 1.1744. Min Range: -1.1744

Max Act: 0.9695. Min Act: -0.0000

Data Index: 1476231 (The Pile)

Max Activating Token Index: 75

Text #15

Max Range: 1.1744. Min Range: -1.1744

Max Act: 0.9678. Min Act: -0.0000

Data Index: 1312138 (The Pile)

Max Activating Token Index: 1007

Text #16

Max Range: 1.1744. Min Range: -1.1744

Max Act: 0.9637. Min Act: -0.0000

Data Index: 136848 (The Pile)

Max Activating Token Index: 454

Text #17

Max Range: 1.1744. Min Range: -1.1744

Max Act: 0.9226. Min Act: -0.0001

Data Index: 1693401 (The Pile)

Max Activating Token Index: 1008

Text #18

Max Range: 1.1744. Min Range: -1.1744

Max Act: 0.9774. Min Act: -0.0000

Data Index: 244457 (The Pile)

Max Activating Token Index: 1005

Text #19

Max Range: 1.1744. Min Range: -1.1744

Max Act: 0.9471. Min Act: -0.0000

Data Index: 1681661 (The Pile)

Max Activating Token Index: 321