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

Dataset: The Pile

Neuron 3503 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: 0.9523. Min Range: -0.9523

Max Act: 0.9523. Min Act: -0.0000

Data Index: 1597888 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7960. Min Act: -0.0000

Data Index: 524086 (The Pile)

Max Activating Token Index: 188

Text #2

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7665. Min Act: -0.0000

Data Index: 1675067 (The Pile)

Max Activating Token Index: 355

Text #3

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7980. Min Act: -0.0000

Data Index: 958833 (The Pile)

Max Activating Token Index: 240

Text #4

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1348093 (The Pile)

Max Activating Token Index: 766

Text #5

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7561. Min Act: -0.0000

Data Index: 1750549 (The Pile)

Max Activating Token Index: 206

Text #6

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7249. Min Act: -0.0000

Data Index: 341751 (The Pile)

Max Activating Token Index: 401

Text #7

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.6841. Min Act: -0.0000

Data Index: 1540748 (The Pile)

Max Activating Token Index: 387

Text #8

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.6795. Min Act: -0.0000

Data Index: 258857 (The Pile)

Max Activating Token Index: 327

Text #9

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1748396 (The Pile)

Max Activating Token Index: 164

Text #10

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.6958. Min Act: -0.0000

Data Index: 905255 (The Pile)

Max Activating Token Index: 210

Text #11

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1718708 (The Pile)

Max Activating Token Index: 933

Text #12

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.6919. Min Act: -0.0000

Data Index: 55000 (The Pile)

Max Activating Token Index: 381

Text #13

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.6482. Min Act: -0.0000

Data Index: 525748 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.6511. Min Act: -0.0000

Data Index: 3242 (The Pile)

Max Activating Token Index: 93

Text #15

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.7098. Min Act: -0.0000

Data Index: 1003779 (The Pile)

Max Activating Token Index: 277

Text #16

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1534039 (The Pile)

Max Activating Token Index: 322

Text #17

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.6321. Min Act: -0.0000

Data Index: 599774 (The Pile)

Max Activating Token Index: 315

Text #18

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1177148 (The Pile)

Max Activating Token Index: 550

Text #19

Max Range: 0.9523. Min Range: -0.9523

Max Act: 0.6591. Min Act: -0.0000

Data Index: 1785475 (The Pile)

Max Activating Token Index: 325