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

Dataset: The Pile

Neuron 2099 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: 1.7159. Min Range: -1.7159

Max Act: 1.7159. Min Act: -0.0000

Data Index: 231426 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.6876. Min Act: -0.0000

Data Index: 1879078 (The Pile)

Max Activating Token Index: 157

Text #2

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.5760. Min Act: -0.0000

Data Index: 746602 (The Pile)

Max Activating Token Index: 91

Text #3

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3778. Min Act: -0.0000

Data Index: 1148068 (The Pile)

Max Activating Token Index: 634

Text #4

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3999. Min Act: -0.0000

Data Index: 678046 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3446. Min Act: -0.0000

Data Index: 483282 (The Pile)

Max Activating Token Index: 948

Text #6

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.5084. Min Act: -0.0000

Data Index: 664416 (The Pile)

Max Activating Token Index: 968

Text #7

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3543. Min Act: -0.0000

Data Index: 1615700 (The Pile)

Max Activating Token Index: 528

Text #8

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3754. Min Act: -0.0000

Data Index: 1360124 (The Pile)

Max Activating Token Index: 668

Text #9

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3640. Min Act: -0.0000

Data Index: 1237464 (The Pile)

Max Activating Token Index: 96

Text #10

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.2609. Min Act: -0.0000

Data Index: 1347464 (The Pile)

Max Activating Token Index: 677

Text #11

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.2680. Min Act: -0.0000

Data Index: 671854 (The Pile)

Max Activating Token Index: 135

Text #12

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3948. Min Act: -0.0000

Data Index: 1258481 (The Pile)

Max Activating Token Index: 687

Text #13

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3654. Min Act: -0.0000

Data Index: 1619672 (The Pile)

Max Activating Token Index: 790

Text #14

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3621. Min Act: -0.0000

Data Index: 1692674 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.2371. Min Act: -0.0000

Data Index: 575420 (The Pile)

Max Activating Token Index: 489

Text #16

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3121. Min Act: -0.0000

Data Index: 627076 (The Pile)

Max Activating Token Index: 179

Text #17

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.2033. Min Act: -0.0000

Data Index: 700716 (The Pile)

Max Activating Token Index: 793

Text #18

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3405. Min Act: -0.0000

Data Index: 838851 (The Pile)

Max Activating Token Index: 560

Text #19

Max Range: 1.7159. Min Range: -1.7159

Max Act: 1.3436. Min Act: -0.0000

Data Index: 87117 (The Pile)

Max Activating Token Index: 99