Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 175 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6881. Min Act: -0.0000

Data Index: 916642 (The Pile)

Max Activating Token Index: 898

Text #1

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5023. Min Act: -0.0000

Data Index: 756634 (The Pile)

Max Activating Token Index: 803

Text #2

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5112. Min Act: -0.0000

Data Index: 624240 (The Pile)

Max Activating Token Index: 229

Text #3

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5014. Min Act: -0.0000

Data Index: 1023221 (The Pile)

Max Activating Token Index: 880

Text #4

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4924. Min Act: -0.0000

Data Index: 959591 (The Pile)

Max Activating Token Index: 571

Text #5

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4886. Min Act: -0.0000

Data Index: 1586421 (The Pile)

Max Activating Token Index: 419

Text #6

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1703896 (The Pile)

Max Activating Token Index: 971

Text #7

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4991. Min Act: -0.0000

Data Index: 444544 (The Pile)

Max Activating Token Index: 176

Text #8

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1037406 (The Pile)

Max Activating Token Index: 238

Text #9

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1635183 (The Pile)

Max Activating Token Index: 976

Text #10

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4663. Min Act: -0.0000

Data Index: 353912 (The Pile)

Max Activating Token Index: 195

Text #11

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1543830 (The Pile)

Max Activating Token Index: 852

Text #12

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4697. Min Act: -0.0000

Data Index: 651841 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1210374 (The Pile)

Max Activating Token Index: 772

Text #14

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4575. Min Act: -0.0000

Data Index: 143172 (The Pile)

Max Activating Token Index: 642

Text #15

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4666. Min Act: -0.0000

Data Index: 1821880 (The Pile)

Max Activating Token Index: 379

Text #16

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1662609 (The Pile)

Max Activating Token Index: 997

Text #17

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4688. Min Act: -0.0000

Data Index: 124158 (The Pile)

Max Activating Token Index: 813

Text #18

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4656. Min Act: -0.0000

Data Index: 377424 (The Pile)

Max Activating Token Index: 1004

Text #19

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4755. Min Act: -0.0000

Data Index: 950038 (The Pile)

Max Activating Token Index: 97