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

Dataset: The Pile

Neuron 2160 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8673. Min Range: -5.8673

Max Act: 5.8673. Min Act: -0.0000

Data Index: 1260192 (The Pile)

Max Activating Token Index: 764

Text #1

Max Range: 5.8673. Min Range: -5.8673

Max Act: 4.4488. Min Act: -0.0000

Data Index: 1320425 (The Pile)

Max Activating Token Index: 347

Text #2

Max Range: 5.8673. Min Range: -5.8673

Max Act: 3.7414. Min Act: -0.0000

Data Index: 760925 (The Pile)

Max Activating Token Index: 685

Text #3

Max Range: 5.8673. Min Range: -5.8673

Max Act: 3.4156. Min Act: -0.0000

Data Index: 197505 (The Pile)

Max Activating Token Index: 789

Text #4

Max Range: 5.8673. Min Range: -5.8673

Max Act: 3.4188. Min Act: -0.0000

Data Index: 358302 (The Pile)

Max Activating Token Index: 32

Text #5

Max Range: 5.8673. Min Range: -5.8673

Max Act: 2.9436. Min Act: -0.0000

Data Index: 1210006 (The Pile)

Max Activating Token Index: 792

Text #6

Max Range: 5.8673. Min Range: -5.8673

Max Act: 2.8849. Min Act: -0.0000

Data Index: 669499 (The Pile)

Max Activating Token Index: 415

Text #7

Max Range: 5.8673. Min Range: -5.8673

Max Act: 2.9423. Min Act: -0.0000

Data Index: 1613520 (The Pile)

Max Activating Token Index: 824

Text #8

Max Range: 5.8673. Min Range: -5.8673

Max Act: 3.0754. Min Act: -0.0000

Data Index: 377387 (The Pile)

Max Activating Token Index: 66

Text #9

Max Range: 5.8673. Min Range: -5.8673

Max Act: 2.7824. Min Act: -0.0000

Data Index: 1077548 (The Pile)

Max Activating Token Index: 459

Text #10

Max Range: 5.8673. Min Range: -5.8673

Max Act: 2.7155. Min Act: -0.0000

Data Index: 1085551 (The Pile)

Max Activating Token Index: 313

Text #11

Max Range: 5.8673. Min Range: -5.8673

Max Act: 2.5161. Min Act: -0.0000

Data Index: 667793 (The Pile)

Max Activating Token Index: 670

Text #12

Max Range: 5.8673. Min Range: -5.8673

Max Act: 2.5562. Min Act: -0.0000

Data Index: 1899608 (The Pile)

Max Activating Token Index: 197

Text #13

Max Range: 5.8673. Min Range: -5.8673

Max Act: 2.4155. Min Act: -0.0000

Data Index: 946161 (The Pile)

Max Activating Token Index: 122

Text #14

Max Range: 5.8673. Min Range: -5.8673

Max Act: 2.2701. Min Act: 0.0000

Data Index: 279788 (The Pile)

Max Activating Token Index: 672

Text #15

Max Range: 5.8673. Min Range: -5.8673

Max Act: 2.2828. Min Act: -0.0000

Data Index: 1760203 (The Pile)

Max Activating Token Index: 753

Text #16

Max Range: 5.8673. Min Range: -5.8673

Max Act: 2.3692. Min Act: -0.0000

Data Index: 1767490 (The Pile)

Max Activating Token Index: 220

Text #17

Max Range: 5.8673. Min Range: -5.8673

Max Act: 2.2360. Min Act: -0.0000

Data Index: 1608419 (The Pile)

Max Activating Token Index: 866

Text #18

Max Range: 5.8673. Min Range: -5.8673

Max Act: 2.4747. Min Act: -0.0000

Data Index: 538351 (The Pile)

Max Activating Token Index: 57

Text #19

Max Range: 5.8673. Min Range: -5.8673

Max Act: 2.3057. Min Act: -0.0000

Data Index: 224953 (The Pile)

Max Activating Token Index: 234