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

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

Neuron 1483 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2594. Min Act: -0.0001

Data Index: 247978 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2755. Min Act: -0.0001

Data Index: 229843 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2628. Min Act: -0.0001

Data Index: 995373 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2613. Min Act: -0.0001

Data Index: 630065 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2671. Min Act: -0.0001

Data Index: 427949 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2699. Min Act: -0.0001

Data Index: 1328096 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2631. Min Act: -0.0001

Data Index: 74222 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2610. Min Act: -0.0001

Data Index: 668010 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2420. Min Act: -0.0001

Data Index: 631874 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2724. Min Act: -0.0001

Data Index: 1258572 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2461. Min Act: -0.0001

Data Index: 1097116 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2525. Min Act: -0.0001

Data Index: 248651 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2717. Min Act: -0.0001

Data Index: 600963 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2430. Min Act: -0.0001

Data Index: 386743 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2383. Min Act: -0.0001

Data Index: 614757 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2469. Min Act: -0.0001

Data Index: 471543 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2378. Min Act: -0.0001

Data Index: 1091363 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2458. Min Act: -0.0001

Data Index: 518965 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2355. Min Act: -0.0001

Data Index: 309036 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 0.2755. Min Range: -0.2755

Max Act: 0.2524. Min Act: -0.0001

Data Index: 65564 (C4 (Web Text))

Max Activating Token Index: 45