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

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

Neuron 1703 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: 2.1938. Min Range: -2.1938

Max Act: 2.1938. Min Act: -0.0001

Data Index: 190578 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 2.1938. Min Range: -2.1938

Max Act: 2.1238. Min Act: -0.0001

Data Index: 323784 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.8493. Min Act: -0.0001

Data Index: 178586 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.4782. Min Act: -0.0001

Data Index: 604023 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.6298. Min Act: -0.0001

Data Index: 867024 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.5239. Min Act: -0.0001

Data Index: 1264122 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.3827. Min Act: -0.0001

Data Index: 1208765 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.4697. Min Act: -0.0001

Data Index: 365874 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.3379. Min Act: -0.0001

Data Index: 1098972 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.4588. Min Act: -0.0001

Data Index: 744984 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.3154. Min Act: -0.0001

Data Index: 584020 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.4807. Min Act: -0.0001

Data Index: 806735 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.4806. Min Act: -0.0001

Data Index: 820640 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.4612. Min Act: -0.0001

Data Index: 842010 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.4954. Min Act: -0.0001

Data Index: 706130 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.3811. Min Act: -0.0001

Data Index: 1150606 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.4524. Min Act: -0.0001

Data Index: 1239569 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.5080. Min Act: -0.0001

Data Index: 103115 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.3739. Min Act: -0.0001

Data Index: 1027287 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 2.1938. Min Range: -2.1938

Max Act: 1.3511. Min Act: -0.0001

Data Index: 596748 (C4 (Web Text))

Max Activating Token Index: 4