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

Dataset: The Pile

Neuron 1411 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3851. Min Act: -0.0000

Data Index: 504560 (The Pile)

Max Activating Token Index: 39

Text #1

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3460. Min Act: -0.0000

Data Index: 917688 (The Pile)

Max Activating Token Index: 413

Text #2

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3231. Min Act: -0.0000

Data Index: 1671880 (The Pile)

Max Activating Token Index: 974

Text #3

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3040. Min Act: -0.0000

Data Index: 987129 (The Pile)

Max Activating Token Index: 13

Text #4

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2866. Min Act: -0.0000

Data Index: 137030 (The Pile)

Max Activating Token Index: 89

Text #5

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1370857 (The Pile)

Max Activating Token Index: 415

Text #6

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2819. Min Act: -0.0000

Data Index: 247936 (The Pile)

Max Activating Token Index: 37

Text #7

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2867. Min Act: -0.0000

Data Index: 1946663 (The Pile)

Max Activating Token Index: 125

Text #8

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.3045. Min Act: -0.0000

Data Index: 483747 (The Pile)

Max Activating Token Index: 89

Text #9

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2676. Min Act: -0.0000

Data Index: 524833 (The Pile)

Max Activating Token Index: 18

Text #10

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1290073 (The Pile)

Max Activating Token Index: 106

Text #11

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1002710 (The Pile)

Max Activating Token Index: 22

Text #12

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2930. Min Act: -0.0000

Data Index: 835747 (The Pile)

Max Activating Token Index: 121

Text #13

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2806. Min Act: -0.0000

Data Index: 505675 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1800920 (The Pile)

Max Activating Token Index: 799

Text #15

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1722221 (The Pile)

Max Activating Token Index: 335

Text #16

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1967195 (The Pile)

Max Activating Token Index: 400

Text #17

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1936096 (The Pile)

Max Activating Token Index: 630

Text #18

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1672578 (The Pile)

Max Activating Token Index: 250

Text #19

Max Range: 0.3851. Min Range: -0.3851

Max Act: 0.2705. Min Act: -0.0000

Data Index: 422830 (The Pile)

Max Activating Token Index: 954