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

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

Neuron 4014 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: 3.7427. Min Range: -3.7427

Max Act: 3.5766. Min Act: -0.0000

Data Index: 1465491 (Python Code)

Max Activating Token Index: 92

Text #1

Max Range: 3.7427. Min Range: -3.7427

Max Act: 3.7427. Min Act: -0.0000

Data Index: 1458851 (Python Code)

Max Activating Token Index: 230

Text #2

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.9039. Min Act: -0.0000

Data Index: 1497851 (Python Code)

Max Activating Token Index: 85

Text #3

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.8334. Min Act: -0.0000

Data Index: 1601946 (Python Code)

Max Activating Token Index: 770

Text #4

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.9488. Min Act: -0.0000

Data Index: 1566913 (Python Code)

Max Activating Token Index: 937

Text #5

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.7784. Min Act: -0.0000

Data Index: 263313 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.7017. Min Act: -0.0000

Data Index: 1577780 (Python Code)

Max Activating Token Index: 729

Text #7

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.7555. Min Act: -0.0000

Data Index: 1433203 (Python Code)

Max Activating Token Index: 965

Text #8

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.7679. Min Act: -0.0000

Data Index: 1375860 (Python Code)

Max Activating Token Index: 31

Text #9

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.6419. Min Act: -0.0000

Data Index: 1627734 (Python Code)

Max Activating Token Index: 269

Text #10

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.7187. Min Act: -0.0000

Data Index: 407219 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.5846. Min Act: -0.0000

Data Index: 950057 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.6906. Min Act: -0.0000

Data Index: 93976 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.4043. Min Act: -0.0000

Data Index: 510363 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.6633. Min Act: -0.0000

Data Index: 1477769 (Python Code)

Max Activating Token Index: 863

Text #15

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.5167. Min Act: -0.0000

Data Index: 1443682 (Python Code)

Max Activating Token Index: 145

Text #16

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.5143. Min Act: -0.0000

Data Index: 47499 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.3848. Min Act: -0.0000

Data Index: 1468855 (Python Code)

Max Activating Token Index: 458

Text #18

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.4864. Min Act: -0.0000

Data Index: 484599 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 3.7427. Min Range: -3.7427

Max Act: 2.4732. Min Act: -0.0000

Data Index: 1641568 (Python Code)

Max Activating Token Index: 882