Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1353 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0970. Min Act: -0.0003

Data Index: 8877 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0797. Min Act: -0.0003

Data Index: 392878 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0812. Min Act: -0.0003

Data Index: 937498 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0776. Min Act: -0.0003

Data Index: 357121 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0716. Min Act: -0.0003

Data Index: 584995 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0717. Min Act: -0.0003

Data Index: 1068901 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0698. Min Act: -0.0003

Data Index: 1341894 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0669. Min Act: -0.0003

Data Index: 732017 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0651. Min Act: -0.0003

Data Index: 165975 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0675. Min Act: -0.0003

Data Index: 382274 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0677. Min Act: -0.0003

Data Index: 1093956 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0660. Min Act: -0.0003

Data Index: 177794 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0629. Min Act: -0.0003

Data Index: 1272642 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0663. Min Act: -0.0003

Data Index: 484297 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0654. Min Act: -0.0003

Data Index: 1063089 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1009835 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0632. Min Act: -0.0003

Data Index: 426455 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0621. Min Act: -0.0003

Data Index: 564575 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0634. Min Act: -0.0003

Data Index: 787575 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0632. Min Act: -0.0003

Data Index: 391802 (C4 (Web Text))

Max Activating Token Index: 46