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

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

Neuron 3730 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1668. Min Act: -0.0001

Data Index: 900856 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1146577 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1742. Min Act: -0.0000

Data Index: 1575339 (Python Code)

Max Activating Token Index: 619

Text #3

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1550107 (Python Code)

Max Activating Token Index: 464

Text #4

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1637. Min Act: -0.0000

Data Index: 326483 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1382383 (Python Code)

Max Activating Token Index: 900

Text #6

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1547. Min Act: -0.0000

Data Index: 1599695 (Python Code)

Max Activating Token Index: 295

Text #7

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1485. Min Act: -0.0001

Data Index: 1635434 (Python Code)

Max Activating Token Index: 754

Text #8

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1489836 (Python Code)

Max Activating Token Index: 266

Text #9

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1503. Min Act: -0.0001

Data Index: 1361998 (Python Code)

Max Activating Token Index: 944

Text #10

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1348283 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1483. Min Act: -0.0001

Data Index: 1501397 (Python Code)

Max Activating Token Index: 614

Text #12

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1454. Min Act: -0.0001

Data Index: 635673 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1454. Min Act: -0.0000

Data Index: 538377 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1491. Min Act: -0.0000

Data Index: 415673 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1513814 (Python Code)

Max Activating Token Index: 55

Text #16

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1393. Min Act: -0.0001

Data Index: 1638676 (Python Code)

Max Activating Token Index: 595

Text #17

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1432. Min Act: -0.0000

Data Index: 505589 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1317. Min Act: -0.0000

Data Index: 1636610 (Python Code)

Max Activating Token Index: 568

Text #19

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1521178 (Python Code)

Max Activating Token Index: 320