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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3115 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0979. Min Act: -0.0002

Data Index: 247074 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0913. Min Act: -0.0002

Data Index: 1190601 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0849. Min Act: -0.0002

Data Index: 640885 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0874. Min Act: -0.0002

Data Index: 870517 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0944. Min Act: -0.0002

Data Index: 178584 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1095385 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0892. Min Act: -0.0002

Data Index: 299006 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0802. Min Act: -0.0002

Data Index: 862315 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1009429 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0854. Min Act: -0.0002

Data Index: 882235 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1042577 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0790. Min Act: -0.0002

Data Index: 89653 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0707. Min Act: -0.0002

Data Index: 703074 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1013392 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0796. Min Act: -0.0002

Data Index: 142559 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0881. Min Act: -0.0002

Data Index: 39922 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0765. Min Act: -0.0002

Data Index: 114595 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0741. Min Act: -0.0002

Data Index: 51071 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1137738 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0765. Min Act: -0.0002

Data Index: 54755 (C4 (Web Text))

Max Activating Token Index: 10