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

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

Neuron 3665 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: 0.0826. Min Range: -0.0826

Max Act: 0.0826. Min Act: -0.0002

Data Index: 311075 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1244145 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0749. Min Act: -0.0002

Data Index: 77986 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0733. Min Act: -0.0002

Data Index: 637753 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0752. Min Act: -0.0002

Data Index: 450598 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0691. Min Act: -0.0002

Data Index: 273839 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1283234 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0601. Min Act: -0.0002

Data Index: 424017 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1029450 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0602. Min Act: -0.0002

Data Index: 303119 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0533. Min Act: -0.0002

Data Index: 95627 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1128680 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0542. Min Act: -0.0002

Data Index: 282810 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1451084 (Python Code)

Max Activating Token Index: 654

Text #14

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1233508 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0536. Min Act: -0.0002

Data Index: 214765 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0504. Min Act: -0.0002

Data Index: 291528 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0507. Min Act: -0.0002

Data Index: 200363 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0513. Min Act: -0.0002

Data Index: 733212 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.0826. Min Range: -0.0826

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1259235 (C4 (Web Text))

Max Activating Token Index: 942