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

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

Neuron 4410 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5586. Min Range: -2.5586

Max Act: 2.5586. Min Act: -0.0000

Data Index: 1546703 (Python Code)

Max Activating Token Index: 628

Text #1

Max Range: 2.5586. Min Range: -2.5586

Max Act: 2.1643. Min Act: -0.0000

Data Index: 1640475 (Python Code)

Max Activating Token Index: 941

Text #2

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.9923. Min Act: -0.0000

Data Index: 1383066 (Python Code)

Max Activating Token Index: 263

Text #3

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.9092. Min Act: -0.0000

Data Index: 1630583 (Python Code)

Max Activating Token Index: 680

Text #4

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.6644. Min Act: -0.0000

Data Index: 1367267 (Python Code)

Max Activating Token Index: 287

Text #5

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.9597. Min Act: -0.0000

Data Index: 1433661 (Python Code)

Max Activating Token Index: 489

Text #6

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.7380. Min Act: -0.0000

Data Index: 1415369 (Python Code)

Max Activating Token Index: 733

Text #7

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.7293. Min Act: -0.0000

Data Index: 1501584 (Python Code)

Max Activating Token Index: 693

Text #8

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.8432. Min Act: -0.0000

Data Index: 1578340 (Python Code)

Max Activating Token Index: 460

Text #9

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.6798. Min Act: -0.0000

Data Index: 1638089 (Python Code)

Max Activating Token Index: 717

Text #10

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.4692. Min Act: -0.0000

Data Index: 1495869 (Python Code)

Max Activating Token Index: 574

Text #11

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.5401. Min Act: -0.0000

Data Index: 1531949 (Python Code)

Max Activating Token Index: 454

Text #12

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.2630. Min Act: -0.0000

Data Index: 1540364 (Python Code)

Max Activating Token Index: 678

Text #13

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.4707. Min Act: -0.0000

Data Index: 1542608 (Python Code)

Max Activating Token Index: 507

Text #14

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.4196. Min Act: -0.0000

Data Index: 117969 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.6879. Min Act: -0.0000

Data Index: 1655024 (Python Code)

Max Activating Token Index: 919

Text #16

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.4982. Min Act: -0.0000

Data Index: 959952 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.2476. Min Act: -0.0000

Data Index: 1626290 (Python Code)

Max Activating Token Index: 727

Text #18

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.3803. Min Act: -0.0000

Data Index: 1383810 (Python Code)

Max Activating Token Index: 975

Text #19

Max Range: 2.5586. Min Range: -2.5586

Max Act: 1.2180. Min Act: -0.0000

Data Index: 1503404 (Python Code)

Max Activating Token Index: 532