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

Dataset: The Pile

Neuron 1574 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.9462. Min Act: -0.0000

Data Index: 791797 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.8478. Min Act: -0.0000

Data Index: 236763 (The Pile)

Max Activating Token Index: 751

Text #2

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.7643. Min Act: -0.0000

Data Index: 1491467 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.7813. Min Act: -0.0000

Data Index: 1400914 (The Pile)

Max Activating Token Index: 478

Text #4

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.8293. Min Act: -0.0000

Data Index: 1391452 (The Pile)

Max Activating Token Index: 999

Text #5

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.7122. Min Act: -0.0000

Data Index: 1261730 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.5875. Min Act: -0.0000

Data Index: 1614 (The Pile)

Max Activating Token Index: 824

Text #7

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.6871. Min Act: -0.0000

Data Index: 1949451 (The Pile)

Max Activating Token Index: 782

Text #8

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.6489. Min Act: -0.0000

Data Index: 1782087 (The Pile)

Max Activating Token Index: 924

Text #9

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.5434. Min Act: -0.0001

Data Index: 1872687 (The Pile)

Max Activating Token Index: 979

Text #10

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.5342. Min Act: -0.0000

Data Index: 987233 (The Pile)

Max Activating Token Index: 895

Text #11

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.5384. Min Act: -0.0000

Data Index: 812765 (The Pile)

Max Activating Token Index: 726

Text #12

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.4662. Min Act: -0.0000

Data Index: 1525887 (The Pile)

Max Activating Token Index: 946

Text #13

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.6061. Min Act: -0.0000

Data Index: 1503007 (The Pile)

Max Activating Token Index: 495

Text #14

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.5949. Min Act: -0.0000

Data Index: 1222115 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.5506. Min Act: -0.0000

Data Index: 659006 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.4986. Min Act: -0.0000

Data Index: 1076448 (The Pile)

Max Activating Token Index: 959

Text #17

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.6819. Min Act: -0.0000

Data Index: 1036162 (The Pile)

Max Activating Token Index: 994

Text #18

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.4630. Min Act: -0.0000

Data Index: 1572403 (The Pile)

Max Activating Token Index: 903

Text #19

Max Range: 1.9462. Min Range: -1.9462

Max Act: 1.5302. Min Act: -0.0000

Data Index: 694009 (The Pile)

Max Activating Token Index: 478