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

Dataset: The Pile

Neuron 2338 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: 0.3632. Min Range: -0.3632

Max Act: 0.3632. Min Act: -0.0000

Data Index: 1212757 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1672619 (The Pile)

Max Activating Token Index: 1003

Text #2

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3081. Min Act: -0.0000

Data Index: 1036397 (The Pile)

Max Activating Token Index: 159

Text #3

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3051. Min Act: -0.0000

Data Index: 241404 (The Pile)

Max Activating Token Index: 522

Text #4

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3032. Min Act: -0.0000

Data Index: 644017 (The Pile)

Max Activating Token Index: 743

Text #5

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1733935 (The Pile)

Max Activating Token Index: 795

Text #6

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3118. Min Act: -0.0000

Data Index: 1081073 (The Pile)

Max Activating Token Index: 231

Text #7

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1262812 (The Pile)

Max Activating Token Index: 1004

Text #8

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3352. Min Act: -0.0001

Data Index: 243368 (The Pile)

Max Activating Token Index: 974

Text #9

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2965. Min Act: -0.0000

Data Index: 667805 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2782. Min Act: -0.0000

Data Index: 617156 (The Pile)

Max Activating Token Index: 925

Text #11

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2879. Min Act: -0.0000

Data Index: 32199 (The Pile)

Max Activating Token Index: 107

Text #12

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2984. Min Act: -0.0000

Data Index: 80237 (The Pile)

Max Activating Token Index: 437

Text #13

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1038818 (The Pile)

Max Activating Token Index: 797

Text #14

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2717. Min Act: -0.0000

Data Index: 1162667 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2909. Min Act: -0.0000

Data Index: 1012190 (The Pile)

Max Activating Token Index: 1010

Text #16

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1194555 (The Pile)

Max Activating Token Index: 797

Text #17

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1024931 (The Pile)

Max Activating Token Index: 679

Text #18

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2729. Min Act: -0.0000

Data Index: 145718 (The Pile)

Max Activating Token Index: 774

Text #19

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2639. Min Act: -0.0000

Data Index: 1501127 (The Pile)

Max Activating Token Index: 877