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

Dataset: The Pile

Neuron 2022 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: 1.0447. Min Range: -1.0447

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1392241 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 1.0447. Min Range: -1.0447

Max Act: 1.0447. Min Act: -0.0000

Data Index: 1840161 (The Pile)

Max Activating Token Index: 697

Text #2

Max Range: 1.0447. Min Range: -1.0447

Max Act: 1.0360. Min Act: -0.0000

Data Index: 1468000 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1454015 (The Pile)

Max Activating Token Index: 645

Text #4

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1411296 (The Pile)

Max Activating Token Index: 848

Text #5

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8577. Min Act: -0.0000

Data Index: 1286538 (The Pile)

Max Activating Token Index: 680

Text #6

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7797. Min Act: -0.0000

Data Index: 247663 (The Pile)

Max Activating Token Index: 113

Text #7

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7321. Min Act: -0.0000

Data Index: 141713 (The Pile)

Max Activating Token Index: 1008

Text #8

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1939975 (The Pile)

Max Activating Token Index: 745

Text #9

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8801. Min Act: -0.0000

Data Index: 203141 (The Pile)

Max Activating Token Index: 245

Text #10

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.8725. Min Act: -0.0000

Data Index: 1746044 (The Pile)

Max Activating Token Index: 187

Text #11

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1078840 (The Pile)

Max Activating Token Index: 904

Text #12

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7269. Min Act: -0.0000

Data Index: 871179 (The Pile)

Max Activating Token Index: 758

Text #13

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7460. Min Act: -0.0000

Data Index: 364907 (The Pile)

Max Activating Token Index: 101

Text #14

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7342. Min Act: -0.0000

Data Index: 1825996 (The Pile)

Max Activating Token Index: 483

Text #15

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6290. Min Act: -0.0000

Data Index: 691883 (The Pile)

Max Activating Token Index: 869

Text #16

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1220798 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7385. Min Act: -0.0000

Data Index: 1594699 (The Pile)

Max Activating Token Index: 748

Text #18

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1221899 (The Pile)

Max Activating Token Index: 983

Text #19

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7330. Min Act: -0.0000

Data Index: 1650718 (The Pile)

Max Activating Token Index: 508