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

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

Neuron 4980 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2945. Min Range: -2.2945

Max Act: 2.2945. Min Act: -0.0000

Data Index: 1221596 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.9883. Min Act: -0.0000

Data Index: 1010218 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.8804. Min Act: -0.0000

Data Index: 72461 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.8826. Min Act: -0.0000

Data Index: 532138 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.6089. Min Act: -0.0000

Data Index: 447062 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.7229. Min Act: -0.0000

Data Index: 908931 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.7517. Min Act: -0.0000

Data Index: 581360 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.6478. Min Act: -0.0000

Data Index: 131105 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.7638. Min Act: -0.0000

Data Index: 29364 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.6716. Min Act: -0.0001

Data Index: 1293262 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.4818. Min Act: -0.0000

Data Index: 955456 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.5212. Min Act: -0.0001

Data Index: 1026436 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.5548. Min Act: -0.0000

Data Index: 425076 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.5788. Min Act: -0.0000

Data Index: 601812 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.5366. Min Act: -0.0000

Data Index: 228371 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.5879. Min Act: -0.0000

Data Index: 835756 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.4905. Min Act: -0.0000

Data Index: 849021 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.3910. Min Act: -0.0000

Data Index: 777587 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.4969. Min Act: -0.0000

Data Index: 691322 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 2.2945. Min Range: -2.2945

Max Act: 1.4780. Min Act: -0.0000

Data Index: 938130 (C4 (Web Text))

Max Activating Token Index: 794