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

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

Neuron 3941 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1646. Min Range: -2.1646

Max Act: 2.1646. Min Act: -0.0000

Data Index: 919958 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.7896. Min Act: -0.0000

Data Index: 673468 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.5745. Min Act: -0.0000

Data Index: 686082 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.4705. Min Act: -0.0000

Data Index: 1248183 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.4164. Min Act: -0.0000

Data Index: 340909 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.4196. Min Act: -0.0000

Data Index: 487348 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.2474. Min Act: -0.0001

Data Index: 856059 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.3607. Min Act: -0.0000

Data Index: 522855 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.4217. Min Act: -0.0000

Data Index: 1059170 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.4699. Min Act: -0.0000

Data Index: 1170436 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.3191. Min Act: -0.0000

Data Index: 252306 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.3832. Min Act: -0.0000

Data Index: 1099634 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.3638. Min Act: -0.0000

Data Index: 92758 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.3926. Min Act: -0.0000

Data Index: 104390 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.2673. Min Act: -0.0000

Data Index: 861161 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.4205. Min Act: -0.0000

Data Index: 1229707 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.2209. Min Act: -0.0000

Data Index: 735340 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.2582. Min Act: -0.0000

Data Index: 496939 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.2592. Min Act: -0.0000

Data Index: 384307 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 2.1646. Min Range: -2.1646

Max Act: 1.1832. Min Act: -0.0000

Data Index: 998329 (C4 (Web Text))

Max Activating Token Index: 567