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

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

Neuron 3054 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0672. Min Act: -0.0003

Data Index: 81489 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0674. Min Act: -0.0003

Data Index: 673153 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0623. Min Act: -0.0003

Data Index: 42566 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0655. Min Act: -0.0003

Data Index: 160779 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1251870 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0592. Min Act: -0.0003

Data Index: 1103594 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0635. Min Act: -0.0003

Data Index: 1263136 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0599. Min Act: -0.0003

Data Index: 249846 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0596. Min Act: -0.0003

Data Index: 362300 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0558. Min Act: -0.0003

Data Index: 538306 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0575. Min Act: -0.0003

Data Index: 65347 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0566. Min Act: -0.0003

Data Index: 7255 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0569. Min Act: -0.0003

Data Index: 632511 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0567. Min Act: -0.0003

Data Index: 97586 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0539. Min Act: -0.0002

Data Index: 193762 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0551. Min Act: -0.0003

Data Index: 436678 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0558. Min Act: -0.0003

Data Index: 888815 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0552. Min Act: -0.0003

Data Index: 1167334 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0553. Min Act: -0.0003

Data Index: 515607 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0551. Min Act: -0.0003

Data Index: 567998 (C4 (Web Text))

Max Activating Token Index: 300