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

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

Neuron 2655 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.2026. Min Act: -0.0000

Data Index: 683972 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1638791 (Python Code)

Max Activating Token Index: 564

Text #2

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1587. Min Act: -0.0000

Data Index: 1554342 (Python Code)

Max Activating Token Index: 355

Text #3

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1582. Min Act: -0.0000

Data Index: 1571679 (Python Code)

Max Activating Token Index: 242

Text #4

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1615058 (Python Code)

Max Activating Token Index: 818

Text #5

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1746. Min Act: -0.0000

Data Index: 1415113 (Python Code)

Max Activating Token Index: 287

Text #6

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1525. Min Act: -0.0000

Data Index: 307331 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1486. Min Act: -0.0000

Data Index: 782392 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1679. Min Act: -0.0000

Data Index: 1642057 (Python Code)

Max Activating Token Index: 313

Text #9

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1620. Min Act: -0.0000

Data Index: 508568 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1666. Min Act: -0.0000

Data Index: 671955 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1429348 (Python Code)

Max Activating Token Index: 396

Text #12

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1454542 (Python Code)

Max Activating Token Index: 336

Text #13

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1610253 (Python Code)

Max Activating Token Index: 261

Text #14

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1482. Min Act: -0.0000

Data Index: 365254 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1546221 (Python Code)

Max Activating Token Index: 542

Text #16

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1274738 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1384. Min Act: -0.0000

Data Index: 81990 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1388. Min Act: -0.0000

Data Index: 902992 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1374. Min Act: -0.0000

Data Index: 271652 (C4 (Web Text))

Max Activating Token Index: 617