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

Dataset: The Pile

Neuron 4798 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.8870. Min Act: -0.0000

Data Index: 583612 (The Pile)

Max Activating Token Index: 539

Text #1

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.7980. Min Act: -0.0000

Data Index: 1485332 (The Pile)

Max Activating Token Index: 707

Text #2

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.6881. Min Act: -0.0000

Data Index: 1920109 (The Pile)

Max Activating Token Index: 646

Text #3

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.4227. Min Act: -0.0000

Data Index: 975006 (The Pile)

Max Activating Token Index: 779

Text #4

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.7089. Min Act: -0.0000

Data Index: 227102 (The Pile)

Max Activating Token Index: 615

Text #5

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.5072. Min Act: -0.0000

Data Index: 382961 (The Pile)

Max Activating Token Index: 388

Text #6

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.5973. Min Act: -0.0000

Data Index: 1883423 (The Pile)

Max Activating Token Index: 539

Text #7

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.6780. Min Act: -0.0000

Data Index: 346192 (The Pile)

Max Activating Token Index: 486

Text #8

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.5794. Min Act: -0.0000

Data Index: 464095 (The Pile)

Max Activating Token Index: 38

Text #9

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.6520. Min Act: -0.0000

Data Index: 1517388 (The Pile)

Max Activating Token Index: 180

Text #10

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.8286. Min Act: -0.0000

Data Index: 653835 (The Pile)

Max Activating Token Index: 829

Text #11

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.5367. Min Act: -0.0000

Data Index: 594009 (The Pile)

Max Activating Token Index: 440

Text #12

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.6243. Min Act: -0.0000

Data Index: 1539425 (The Pile)

Max Activating Token Index: 876

Text #13

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.6094. Min Act: -0.0000

Data Index: 1245110 (The Pile)

Max Activating Token Index: 97

Text #14

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.5855. Min Act: -0.0000

Data Index: 1973041 (The Pile)

Max Activating Token Index: 519

Text #15

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.4019. Min Act: -0.0000

Data Index: 1434184 (The Pile)

Max Activating Token Index: 792

Text #16

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.5773. Min Act: -0.0000

Data Index: 1394703 (The Pile)

Max Activating Token Index: 768

Text #17

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.4782. Min Act: -0.0000

Data Index: 701087 (The Pile)

Max Activating Token Index: 286

Text #18

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.5466. Min Act: -0.0000

Data Index: 1276482 (The Pile)

Max Activating Token Index: 407

Text #19

Max Range: 1.8870. Min Range: -1.8870

Max Act: 1.4601. Min Act: -0.0000

Data Index: 865759 (The Pile)

Max Activating Token Index: 689