Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3662 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.2687. Min Act: -0.0001

Data Index: 1416549 (Python Code)

Max Activating Token Index: 105

Text #1

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.2259. Min Act: -0.0001

Data Index: 1500346 (Python Code)

Max Activating Token Index: 823

Text #2

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.0760. Min Act: -0.0001

Data Index: 1564678 (Python Code)

Max Activating Token Index: 633

Text #3

Max Range: 1.2687. Min Range: -1.2687

Max Act: 1.0663. Min Act: -0.0001

Data Index: 1429495 (Python Code)

Max Activating Token Index: 759

Text #4

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.9378. Min Act: -0.0001

Data Index: 1568241 (Python Code)

Max Activating Token Index: 172

Text #5

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.9056. Min Act: -0.0001

Data Index: 1627573 (Python Code)

Max Activating Token Index: 453

Text #6

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.8493. Min Act: -0.0001

Data Index: 1458475 (Python Code)

Max Activating Token Index: 973

Text #7

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.8511. Min Act: -0.0001

Data Index: 1416009 (Python Code)

Max Activating Token Index: 315

Text #8

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.8744. Min Act: -0.0001

Data Index: 1513283 (Python Code)

Max Activating Token Index: 25

Text #9

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.8803. Min Act: -0.0001

Data Index: 1417582 (Python Code)

Max Activating Token Index: 240

Text #10

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.7700. Min Act: -0.0001

Data Index: 1629353 (Python Code)

Max Activating Token Index: 119

Text #11

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.8385. Min Act: -0.0001

Data Index: 1416710 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.7851. Min Act: -0.0001

Data Index: 1439342 (Python Code)

Max Activating Token Index: 98

Text #13

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.7819. Min Act: -0.0001

Data Index: 1654955 (Python Code)

Max Activating Token Index: 409

Text #14

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.8012. Min Act: -0.0001

Data Index: 1646023 (Python Code)

Max Activating Token Index: 624

Text #15

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.7875. Min Act: -0.0001

Data Index: 1490395 (Python Code)

Max Activating Token Index: 199

Text #16

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.7692. Min Act: -0.0001

Data Index: 1552708 (Python Code)

Max Activating Token Index: 169

Text #17

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.7623. Min Act: -0.0001

Data Index: 1496445 (Python Code)

Max Activating Token Index: 27

Text #18

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.7328. Min Act: -0.0001

Data Index: 1393046 (Python Code)

Max Activating Token Index: 508

Text #19

Max Range: 1.2687. Min Range: -1.2687

Max Act: 0.7521. Min Act: -0.0001

Data Index: 1410035 (Python Code)

Max Activating Token Index: 71