Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2649 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1716. Min Range: -2.1716

Max Act: 2.0981. Min Act: -0.0000

Data Index: 299672 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 2.1716. Min Range: -2.1716

Max Act: 2.1716. Min Act: -0.0000

Data Index: 1515840 (Python Code)

Max Activating Token Index: 427

Text #2

Max Range: 2.1716. Min Range: -2.1716

Max Act: 1.9971. Min Act: -0.0000

Data Index: 1465657 (Python Code)

Max Activating Token Index: 597

Text #3

Max Range: 2.1716. Min Range: -2.1716

Max Act: 2.0708. Min Act: -0.0000

Data Index: 823171 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 2.1716. Min Range: -2.1716

Max Act: 2.0410. Min Act: -0.0000

Data Index: 1430472 (Python Code)

Max Activating Token Index: 499

Text #5

Max Range: 2.1716. Min Range: -2.1716

Max Act: 1.8767. Min Act: -0.0000

Data Index: 1400007 (Python Code)

Max Activating Token Index: 700

Text #6

Max Range: 2.1716. Min Range: -2.1716

Max Act: 1.8648. Min Act: -0.0000

Data Index: 818214 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 2.1716. Min Range: -2.1716

Max Act: 1.7016. Min Act: -0.0000

Data Index: 786000 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 2.1716. Min Range: -2.1716

Max Act: 1.5420. Min Act: -0.0000

Data Index: 122913 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 2.1716. Min Range: -2.1716

Max Act: 1.5968. Min Act: -0.0000

Data Index: 1127506 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 2.1716. Min Range: -2.1716

Max Act: 1.4950. Min Act: -0.0000

Data Index: 1589237 (Python Code)

Max Activating Token Index: 587

Text #11

Max Range: 2.1716. Min Range: -2.1716

Max Act: 1.4180. Min Act: -0.0000

Data Index: 919621 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 2.1716. Min Range: -2.1716

Max Act: 1.4834. Min Act: -0.0000

Data Index: 1464083 (Python Code)

Max Activating Token Index: 554

Text #13

Max Range: 2.1716. Min Range: -2.1716

Max Act: 1.4618. Min Act: -0.0000

Data Index: 1433128 (Python Code)

Max Activating Token Index: 673

Text #14

Max Range: 2.1716. Min Range: -2.1716

Max Act: 1.4453. Min Act: -0.0000

Data Index: 1655458 (Python Code)

Max Activating Token Index: 518

Text #15

Max Range: 2.1716. Min Range: -2.1716

Max Act: 1.4293. Min Act: -0.0000

Data Index: 1504237 (Python Code)

Max Activating Token Index: 862

Text #16

Max Range: 2.1716. Min Range: -2.1716

Max Act: 1.3022. Min Act: -0.0000

Data Index: 1588403 (Python Code)

Max Activating Token Index: 391

Text #17

Max Range: 2.1716. Min Range: -2.1716

Max Act: 1.3609. Min Act: -0.0000

Data Index: 113868 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 2.1716. Min Range: -2.1716

Max Act: 1.3962. Min Act: -0.0000

Data Index: 1537012 (Python Code)

Max Activating Token Index: 421

Text #19

Max Range: 2.1716. Min Range: -2.1716

Max Act: 1.3204. Min Act: -0.0000

Data Index: 1490663 (Python Code)

Max Activating Token Index: 510