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

Dataset: The Pile

Neuron 1259 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: 1.0927. Min Range: -1.0927

Max Act: 1.0927. Min Act: -0.0001

Data Index: 271592 (The Pile)

Max Activating Token Index: 589

Text #1

Max Range: 1.0927. Min Range: -1.0927

Max Act: 1.0643. Min Act: -0.0000

Data Index: 180259 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 1.0927. Min Range: -1.0927

Max Act: 1.0190. Min Act: -0.0000

Data Index: 1477489 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 1.0927. Min Range: -1.0927

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1514857 (The Pile)

Max Activating Token Index: 789

Text #4

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.9749. Min Act: -0.0000

Data Index: 1661320 (The Pile)

Max Activating Token Index: 564

Text #5

Max Range: 1.0927. Min Range: -1.0927

Max Act: 1.0350. Min Act: -0.0000

Data Index: 364546 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.8182. Min Act: -0.0001

Data Index: 780223 (The Pile)

Max Activating Token Index: 927

Text #7

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.9099. Min Act: -0.0000

Data Index: 627887 (The Pile)

Max Activating Token Index: 924

Text #8

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.8920. Min Act: -0.0001

Data Index: 978808 (The Pile)

Max Activating Token Index: 220

Text #9

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.8970. Min Act: -0.0000

Data Index: 1998329 (The Pile)

Max Activating Token Index: 686

Text #10

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.7951. Min Act: -0.0000

Data Index: 695686 (The Pile)

Max Activating Token Index: 961

Text #11

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.8680. Min Act: -0.0000

Data Index: 1490573 (The Pile)

Max Activating Token Index: 479

Text #12

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.9361. Min Act: -0.0000

Data Index: 518077 (The Pile)

Max Activating Token Index: 505

Text #13

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.8609. Min Act: -0.0000

Data Index: 588130 (The Pile)

Max Activating Token Index: 435

Text #14

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1204363 (The Pile)

Max Activating Token Index: 447

Text #15

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.8893. Min Act: -0.0000

Data Index: 1082224 (The Pile)

Max Activating Token Index: 319

Text #16

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.8945. Min Act: -0.0000

Data Index: 384005 (The Pile)

Max Activating Token Index: 393

Text #17

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.8710. Min Act: -0.0000

Data Index: 216670 (The Pile)

Max Activating Token Index: 644

Text #18

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1958767 (The Pile)

Max Activating Token Index: 998

Text #19

Max Range: 1.0927. Min Range: -1.0927

Max Act: 0.7875. Min Act: -0.0000

Data Index: 1823625 (The Pile)

Max Activating Token Index: 68