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

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

Neuron 3784 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: 0.0832. Min Range: -0.0832

Max Act: 0.0832. Min Act: -0.0002

Data Index: 533842 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1239286 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0778. Min Act: -0.0002

Data Index: 910576 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0701. Min Act: -0.0002

Data Index: 328119 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1024927 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0696. Min Act: -0.0002

Data Index: 440382 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0795. Min Act: -0.0002

Data Index: 131520 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0701. Min Act: -0.0002

Data Index: 892847 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1237514 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1171160 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0730. Min Act: -0.0002

Data Index: 646612 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1264435 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0631. Min Act: -0.0002

Data Index: 88228 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0634. Min Act: -0.0002

Data Index: 882245 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0585. Min Act: -0.0002

Data Index: 741544 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0656. Min Act: -0.0002

Data Index: 139679 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0651. Min Act: -0.0002

Data Index: 29439 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1081033 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0606. Min Act: -0.0002

Data Index: 592119 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0651. Min Act: -0.0002

Data Index: 776149 (C4 (Web Text))

Max Activating Token Index: 333