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

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

Neuron 1107 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.8760. Min Act: -0.0000

Data Index: 875873 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.5835. Min Act: -0.0000

Data Index: 225659 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.4790. Min Act: -0.0000

Data Index: 85448 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 4.8760. Min Range: -4.8760

Max Act: 3.6493. Min Act: -0.0000

Data Index: 1039557 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.3182. Min Act: -0.0000

Data Index: 931949 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.1865. Min Act: -0.0000

Data Index: 337837 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.0241. Min Act: -0.0000

Data Index: 143963 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.0489. Min Act: -0.0000

Data Index: 201351 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.1709. Min Act: -0.0000

Data Index: 1047042 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 4.8760. Min Range: -4.8760

Max Act: 3.9884. Min Act: -0.0000

Data Index: 121092 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.0339. Min Act: -0.0000

Data Index: 717061 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 4.8760. Min Range: -4.8760

Max Act: 4.1742. Min Act: -0.0000

Data Index: 774399 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 4.8760. Min Range: -4.8760

Max Act: 3.9589. Min Act: -0.0000

Data Index: 187974 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 4.8760. Min Range: -4.8760

Max Act: 3.6307. Min Act: -0.0000

Data Index: 374022 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 4.8760. Min Range: -4.8760

Max Act: 3.5307. Min Act: -0.0000

Data Index: 170903 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 4.8760. Min Range: -4.8760

Max Act: 3.8159. Min Act: -0.0000

Data Index: 1352228 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 4.8760. Min Range: -4.8760

Max Act: 3.7942. Min Act: -0.0000

Data Index: 618806 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 4.8760. Min Range: -4.8760

Max Act: 3.7896. Min Act: -0.0000

Data Index: 38618 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 4.8760. Min Range: -4.8760

Max Act: 3.5807. Min Act: -0.0000

Data Index: 1134490 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 4.8760. Min Range: -4.8760

Max Act: 3.6753. Min Act: -0.0000

Data Index: 813629 (C4 (Web Text))

Max Activating Token Index: 574