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

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

Neuron 1564 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.9951. Min Act: -0.0001

Data Index: 613699 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.9789. Min Act: -0.0001

Data Index: 69059 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.7948. Min Act: -0.0001

Data Index: 291223 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.3959. Min Act: -0.0001

Data Index: 548701 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.6859. Min Act: -0.0001

Data Index: 1293384 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.5799. Min Act: -0.0001

Data Index: 1246588 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.7712. Min Act: -0.0001

Data Index: 620896 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.6675. Min Act: -0.0001

Data Index: 263959 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.5286. Min Act: -0.0001

Data Index: 578601 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.4925. Min Act: -0.0001

Data Index: 983612 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.6272. Min Act: -0.0001

Data Index: 1074722 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.4852. Min Act: -0.0001

Data Index: 1123612 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.5654. Min Act: -0.0001

Data Index: 887816 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.4257. Min Act: -0.0001

Data Index: 310794 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.7362. Min Act: -0.0001

Data Index: 1195974 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.4643. Min Act: -0.0001

Data Index: 419028 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.4534. Min Act: -0.0001

Data Index: 745711 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.4916. Min Act: -0.0001

Data Index: 782240 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.4362. Min Act: -0.0001

Data Index: 69478 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.9951. Min Range: -1.9951

Max Act: 1.4472. Min Act: -0.0001

Data Index: 281821 (C4 (Web Text))

Max Activating Token Index: 335