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

Dataset: The Pile

Neuron 2064 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.8070. Min Act: -0.0001

Data Index: 1218276 (The Pile)

Max Activating Token Index: 76

Text #1

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7997. Min Act: -0.0001

Data Index: 1080977 (The Pile)

Max Activating Token Index: 118

Text #2

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7592. Min Act: -0.0001

Data Index: 274983 (The Pile)

Max Activating Token Index: 19

Text #3

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.8080. Min Act: -0.0001

Data Index: 1690795 (The Pile)

Max Activating Token Index: 90

Text #4

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7827. Min Act: -0.0001

Data Index: 1252797 (The Pile)

Max Activating Token Index: 115

Text #5

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7809. Min Act: -0.0001

Data Index: 579138 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7732. Min Act: -0.0001

Data Index: 242957 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7780. Min Act: -0.0001

Data Index: 1331597 (The Pile)

Max Activating Token Index: 877

Text #8

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7614. Min Act: -0.0001

Data Index: 1844853 (The Pile)

Max Activating Token Index: 30

Text #9

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7799. Min Act: -0.0001

Data Index: 209339 (The Pile)

Max Activating Token Index: 74

Text #10

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7682. Min Act: -0.0001

Data Index: 224801 (The Pile)

Max Activating Token Index: 27

Text #11

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7646. Min Act: -0.0001

Data Index: 433159 (The Pile)

Max Activating Token Index: 134

Text #12

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6884. Min Act: -0.0001

Data Index: 1239919 (The Pile)

Max Activating Token Index: 862

Text #13

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7029. Min Act: -0.0001

Data Index: 101703 (The Pile)

Max Activating Token Index: 83

Text #14

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7465. Min Act: -0.0001

Data Index: 1292396 (The Pile)

Max Activating Token Index: 70

Text #15

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7381. Min Act: -0.0001

Data Index: 481043 (The Pile)

Max Activating Token Index: 28

Text #16

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6981. Min Act: -0.0001

Data Index: 1198802 (The Pile)

Max Activating Token Index: 114

Text #17

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.7352. Min Act: -0.0001

Data Index: 900008 (The Pile)

Max Activating Token Index: 457

Text #18

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6790. Min Act: -0.0001

Data Index: 1846516 (The Pile)

Max Activating Token Index: 90

Text #19

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6348. Min Act: -0.0001

Data Index: 1606761 (The Pile)

Max Activating Token Index: 89