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

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

Neuron 3175 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1649. Min Range: -2.1649

Max Act: 2.1649. Min Act: -0.0000

Data Index: 759521 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 2.1649. Min Range: -2.1649

Max Act: 2.0996. Min Act: -0.0000

Data Index: 1365854 (Python Code)

Max Activating Token Index: 667

Text #2

Max Range: 2.1649. Min Range: -2.1649

Max Act: 2.1097. Min Act: -0.0000

Data Index: 180806 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 2.1649. Min Range: -2.1649

Max Act: 2.0516. Min Act: -0.0000

Data Index: 645400 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 2.1649. Min Range: -2.1649

Max Act: 2.0456. Min Act: -0.0000

Data Index: 1043072 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 2.1649. Min Range: -2.1649

Max Act: 1.9819. Min Act: -0.0000

Data Index: 1235905 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 2.1649. Min Range: -2.1649

Max Act: 1.9669. Min Act: -0.0000

Data Index: 1013714 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 2.1649. Min Range: -2.1649

Max Act: 2.0520. Min Act: -0.0000

Data Index: 790926 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 2.1649. Min Range: -2.1649

Max Act: 2.0459. Min Act: -0.0000

Data Index: 1091057 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 2.1649. Min Range: -2.1649

Max Act: 2.1172. Min Act: -0.0000

Data Index: 1634000 (Python Code)

Max Activating Token Index: 617

Text #10

Max Range: 2.1649. Min Range: -2.1649

Max Act: 1.9414. Min Act: -0.0000

Data Index: 1055095 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 2.1649. Min Range: -2.1649

Max Act: 1.7796. Min Act: -0.0000

Data Index: 1377744 (Python Code)

Max Activating Token Index: 860

Text #12

Max Range: 2.1649. Min Range: -2.1649

Max Act: 1.8911. Min Act: -0.0000

Data Index: 1392058 (Python Code)

Max Activating Token Index: 536

Text #13

Max Range: 2.1649. Min Range: -2.1649

Max Act: 1.8721. Min Act: -0.0000

Data Index: 861573 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 2.1649. Min Range: -2.1649

Max Act: 1.9762. Min Act: -0.0000

Data Index: 352322 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 2.1649. Min Range: -2.1649

Max Act: 1.8641. Min Act: -0.0000

Data Index: 292901 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 2.1649. Min Range: -2.1649

Max Act: 1.7316. Min Act: -0.0000

Data Index: 1393450 (Python Code)

Max Activating Token Index: 154

Text #17

Max Range: 2.1649. Min Range: -2.1649

Max Act: 1.8262. Min Act: -0.0000

Data Index: 737737 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 2.1649. Min Range: -2.1649

Max Act: 1.8964. Min Act: -0.0000

Data Index: 1220083 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 2.1649. Min Range: -2.1649

Max Act: 1.7714. Min Act: -0.0000

Data Index: 1434903 (Python Code)

Max Activating Token Index: 394