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

Dataset: The Pile

Neuron 4824 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: 0.9803. Min Range: -0.9803

Max Act: 0.9803. Min Act: -0.0000

Data Index: 551175 (The Pile)

Max Activating Token Index: 89

Text #1

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8922. Min Act: -0.0000

Data Index: 1244136 (The Pile)

Max Activating Token Index: 716

Text #2

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.9137. Min Act: -0.0000

Data Index: 1598340 (The Pile)

Max Activating Token Index: 284

Text #3

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8191. Min Act: -0.0000

Data Index: 1878916 (The Pile)

Max Activating Token Index: 718

Text #4

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1640619 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1528144 (The Pile)

Max Activating Token Index: 186

Text #6

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8137. Min Act: -0.0000

Data Index: 1901565 (The Pile)

Max Activating Token Index: 1019

Text #7

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7730. Min Act: -0.0000

Data Index: 1247093 (The Pile)

Max Activating Token Index: 614

Text #8

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7462. Min Act: -0.0000

Data Index: 840324 (The Pile)

Max Activating Token Index: 850

Text #9

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8057. Min Act: -0.0000

Data Index: 1406099 (The Pile)

Max Activating Token Index: 88

Text #10

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1192879 (The Pile)

Max Activating Token Index: 600

Text #11

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1217456 (The Pile)

Max Activating Token Index: 200

Text #12

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7665. Min Act: -0.0000

Data Index: 1611710 (The Pile)

Max Activating Token Index: 616

Text #13

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7657. Min Act: -0.0000

Data Index: 1976729 (The Pile)

Max Activating Token Index: 748

Text #14

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7606. Min Act: -0.0000

Data Index: 534657 (The Pile)

Max Activating Token Index: 808

Text #15

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7826. Min Act: -0.0000

Data Index: 1340859 (The Pile)

Max Activating Token Index: 515

Text #16

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1020086 (The Pile)

Max Activating Token Index: 954

Text #17

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7652. Min Act: -0.0000

Data Index: 965146 (The Pile)

Max Activating Token Index: 500

Text #18

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1622877 (The Pile)

Max Activating Token Index: 12

Text #19

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7298. Min Act: -0.0000

Data Index: 1515799 (The Pile)

Max Activating Token Index: 1018