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

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

Neuron 2594 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1199. Min Act: -0.0000

Data Index: 860050 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0887. Min Act: -0.0000

Data Index: 711140 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0911. Min Act: -0.0000

Data Index: 49061 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0886. Min Act: -0.0000

Data Index: 21070 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0837. Min Act: -0.0000

Data Index: 609784 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0800. Min Act: -0.0000

Data Index: 147852 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0778. Min Act: -0.0000

Data Index: 695879 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0706. Min Act: -0.0000

Data Index: 1576781 (Python Code)

Max Activating Token Index: 262

Text #8

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0705. Min Act: -0.0000

Data Index: 528506 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0741. Min Act: -0.0000

Data Index: 1600043 (Python Code)

Max Activating Token Index: 175

Text #10

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0752. Min Act: -0.0000

Data Index: 1239463 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0680. Min Act: -0.0000

Data Index: 691718 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0670. Min Act: -0.0000

Data Index: 622273 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0629. Min Act: -0.0000

Data Index: 634286 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0661. Min Act: -0.0000

Data Index: 494709 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0684. Min Act: -0.0000

Data Index: 265812 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0686. Min Act: -0.0000

Data Index: 274168 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0697. Min Act: -0.0000

Data Index: 1175251 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0571. Min Act: -0.0000

Data Index: 1383191 (Python Code)

Max Activating Token Index: 252

Text #19

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0646. Min Act: -0.0000

Data Index: 699879 (C4 (Web Text))

Max Activating Token Index: 647