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

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

Neuron 2829 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4599. Min Range: -3.4599

Max Act: 3.0253. Min Act: -0.0000

Data Index: 1073131 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 3.4599. Min Range: -3.4599

Max Act: 3.4599. Min Act: -0.0001

Data Index: 904793 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.7798. Min Act: -0.0001

Data Index: 702479 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 3.4599. Min Range: -3.4599

Max Act: 3.0601. Min Act: -0.0000

Data Index: 1319079 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.8798. Min Act: -0.0001

Data Index: 720335 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.8508. Min Act: -0.0000

Data Index: 246080 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.5010. Min Act: -0.0001

Data Index: 518253 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.9194. Min Act: -0.0001

Data Index: 105484 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.5031. Min Act: -0.0001

Data Index: 693192 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.4668. Min Act: -0.0000

Data Index: 227403 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.5700. Min Act: -0.0001

Data Index: 1187200 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.8250. Min Act: -0.0000

Data Index: 461608 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.5392. Min Act: -0.0001

Data Index: 1057219 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.6543. Min Act: -0.0000

Data Index: 433030 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.7592. Min Act: -0.0000

Data Index: 243205 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.7689. Min Act: -0.0001

Data Index: 1329647 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.4475. Min Act: -0.0001

Data Index: 1147630 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.3723. Min Act: -0.0001

Data Index: 140880 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 3.4599. Min Range: -3.4599

Max Act: 2.8383. Min Act: -0.0001

Data Index: 1351265 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 3.4599. Min Range: -3.4599

Max Act: 1.6594. Min Act: -0.0000

Data Index: 725632 (C4 (Web Text))

Max Activating Token Index: 614