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

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

Neuron 5062 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: 0.0912. Min Range: -0.0912

Max Act: 0.0912. Min Act: -0.0002

Data Index: 925417 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0874. Min Act: -0.0002

Data Index: 116649 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0814. Min Act: -0.0002

Data Index: 724233 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0804. Min Act: -0.0002

Data Index: 241817 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0743. Min Act: -0.0002

Data Index: 273085 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1259131 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0694. Min Act: -0.0002

Data Index: 325011 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0623. Min Act: -0.0002

Data Index: 350675 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0693. Min Act: -0.0002

Data Index: 646151 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0688. Min Act: -0.0002

Data Index: 856268 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0657. Min Act: -0.0002

Data Index: 382090 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1301303 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0677. Min Act: -0.0002

Data Index: 991171 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1059511 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0623. Min Act: -0.0002

Data Index: 189753 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0627. Min Act: -0.0002

Data Index: 40479 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0606. Min Act: -0.0002

Data Index: 143971 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0602. Min Act: -0.0002

Data Index: 700073 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0572. Min Act: -0.0002

Data Index: 870556 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1280075 (C4 (Web Text))

Max Activating Token Index: 273