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

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

Neuron 2774 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: 0.2066. Min Range: -0.2066

Max Act: 0.2016. Min Act: -0.0001

Data Index: 706224 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1300681 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1703. Min Act: -0.0001

Data Index: 812838 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1692. Min Act: -0.0001

Data Index: 1375684 (Python Code)

Max Activating Token Index: 666

Text #4

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1626. Min Act: -0.0001

Data Index: 1588702 (Python Code)

Max Activating Token Index: 313

Text #5

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1743. Min Act: -0.0001

Data Index: 162312 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1657. Min Act: -0.0001

Data Index: 1387710 (Python Code)

Max Activating Token Index: 640

Text #7

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1266029 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1641. Min Act: -0.0001

Data Index: 1526984 (Python Code)

Max Activating Token Index: 426

Text #9

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1634. Min Act: -0.0001

Data Index: 355432 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1570. Min Act: -0.0000

Data Index: 58715 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1503. Min Act: -0.0001

Data Index: 1523605 (Python Code)

Max Activating Token Index: 517

Text #12

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1602. Min Act: -0.0000

Data Index: 149054 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1505. Min Act: -0.0001

Data Index: 1625390 (Python Code)

Max Activating Token Index: 321

Text #14

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1506. Min Act: -0.0001

Data Index: 1642637 (Python Code)

Max Activating Token Index: 431

Text #15

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1543. Min Act: -0.0000

Data Index: 984702 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1352690 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1421512 (Python Code)

Max Activating Token Index: 330

Text #18

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1446. Min Act: -0.0001

Data Index: 1473713 (Python Code)

Max Activating Token Index: 730

Text #19

Max Range: 0.2066. Min Range: -0.2066

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1390401 (Python Code)

Max Activating Token Index: 836