Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3397 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2694. Min Act: -0.0001

Data Index: 471479 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1863. Min Act: -0.0001

Data Index: 1306696 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1853. Min Act: -0.0001

Data Index: 1267551 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1760. Min Act: -0.0000

Data Index: 160406 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1724. Min Act: -0.0001

Data Index: 102506 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1548. Min Act: -0.0001

Data Index: 419365 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1686. Min Act: -0.0001

Data Index: 618585 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1698. Min Act: -0.0001

Data Index: 58588 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1629. Min Act: -0.0001

Data Index: 668040 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1600. Min Act: -0.0001

Data Index: 274188 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1640. Min Act: -0.0001

Data Index: 295959 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1504919 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1684. Min Act: -0.0001

Data Index: 174463 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1182375 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1596. Min Act: -0.0000

Data Index: 1344468 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1655. Min Act: -0.0000

Data Index: 1339963 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1532. Min Act: -0.0001

Data Index: 458098 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1449. Min Act: -0.0001

Data Index: 422560 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1542. Min Act: -0.0001

Data Index: 1149021 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1529. Min Act: -0.0001

Data Index: 55731 (C4 (Web Text))

Max Activating Token Index: 883