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

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

Neuron 2071 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1824. Min Range: -3.1824

Max Act: 3.1824. Min Act: -0.0000

Data Index: 293769 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.8697. Min Act: -0.0000

Data Index: 376774 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.8726. Min Act: -0.0000

Data Index: 2530 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.7379. Min Act: -0.0000

Data Index: 870881 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.8543. Min Act: -0.0000

Data Index: 1632289 (Python Code)

Max Activating Token Index: 648

Text #5

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.7042. Min Act: -0.0000

Data Index: 102396 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.5785. Min Act: -0.0000

Data Index: 309096 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.5753. Min Act: -0.0000

Data Index: 932171 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.6649. Min Act: -0.0000

Data Index: 708469 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.5255. Min Act: -0.0000

Data Index: 1165235 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.5318. Min Act: -0.0000

Data Index: 563128 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.5163. Min Act: -0.0000

Data Index: 824803 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.4443. Min Act: -0.0000

Data Index: 1213789 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.4441. Min Act: -0.0000

Data Index: 106932 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.4437. Min Act: -0.0000

Data Index: 713007 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.4008. Min Act: -0.0000

Data Index: 847870 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.3905. Min Act: -0.0000

Data Index: 510729 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.3785. Min Act: -0.0000

Data Index: 382363 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.3473. Min Act: -0.0000

Data Index: 609086 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 3.1824. Min Range: -3.1824

Max Act: 2.3638. Min Act: -0.0000

Data Index: 963640 (C4 (Web Text))

Max Activating Token Index: 841