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

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

Neuron 4865 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1033103 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.6719. Min Act: -0.0000

Data Index: 920481 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.6356. Min Act: -0.0000

Data Index: 201376 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.6028. Min Act: -0.0000

Data Index: 838372 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.6079. Min Act: -0.0000

Data Index: 687345 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.6145. Min Act: -0.0000

Data Index: 180278 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5656. Min Act: -0.0000

Data Index: 342367 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5817. Min Act: -0.0000

Data Index: 155295 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5481. Min Act: -0.0000

Data Index: 1104775 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5427. Min Act: -0.0000

Data Index: 954300 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5307. Min Act: -0.0000

Data Index: 728629 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5486. Min Act: -0.0000

Data Index: 42473 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5610. Min Act: -0.0000

Data Index: 767770 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1163942 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5170. Min Act: -0.0000

Data Index: 388049 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.4999. Min Act: -0.0000

Data Index: 18771 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1057422 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5086. Min Act: -0.0000

Data Index: 990195 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.4696. Min Act: -0.0000

Data Index: 356625 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.6776. Min Range: -0.6776

Max Act: 0.5001. Min Act: -0.0000

Data Index: 85786 (C4 (Web Text))

Max Activating Token Index: 253