Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3142 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.0991. Min Range: -4.0991

Max Act: 3.7097. Min Act: -0.0000

Data Index: 1451597 (Python Code)

Max Activating Token Index: 235

Text #1

Max Range: 4.0991. Min Range: -4.0991

Max Act: 3.7104. Min Act: -0.0000

Data Index: 1538478 (Python Code)

Max Activating Token Index: 134

Text #2

Max Range: 4.0991. Min Range: -4.0991

Max Act: 4.0991. Min Act: -0.0000

Data Index: 1655480 (Python Code)

Max Activating Token Index: 204

Text #3

Max Range: 4.0991. Min Range: -4.0991

Max Act: 3.5362. Min Act: -0.0000

Data Index: 1465257 (Python Code)

Max Activating Token Index: 375

Text #4

Max Range: 4.0991. Min Range: -4.0991

Max Act: 3.2482. Min Act: -0.0000

Data Index: 1579275 (Python Code)

Max Activating Token Index: 308

Text #5

Max Range: 4.0991. Min Range: -4.0991

Max Act: 3.5569. Min Act: -0.0000

Data Index: 1444200 (Python Code)

Max Activating Token Index: 420

Text #6

Max Range: 4.0991. Min Range: -4.0991

Max Act: 3.2068. Min Act: -0.0000

Data Index: 1492966 (Python Code)

Max Activating Token Index: 546

Text #7

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.9201. Min Act: -0.0000

Data Index: 1530783 (Python Code)

Max Activating Token Index: 571

Text #8

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.6551. Min Act: -0.0000

Data Index: 1643318 (Python Code)

Max Activating Token Index: 597

Text #9

Max Range: 4.0991. Min Range: -4.0991

Max Act: 1.6033. Min Act: -0.0000

Data Index: 1516404 (Python Code)

Max Activating Token Index: 819

Text #10

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.1785. Min Act: -0.0000

Data Index: 1590145 (Python Code)

Max Activating Token Index: 672

Text #11

Max Range: 4.0991. Min Range: -4.0991

Max Act: 1.8880. Min Act: -0.0000

Data Index: 1533884 (Python Code)

Max Activating Token Index: 661

Text #12

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.0409. Min Act: -0.0000

Data Index: 1525936 (Python Code)

Max Activating Token Index: 958

Text #13

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.2351. Min Act: -0.0000

Data Index: 1632485 (Python Code)

Max Activating Token Index: 1017

Text #14

Max Range: 4.0991. Min Range: -4.0991

Max Act: 1.7834. Min Act: -0.0000

Data Index: 1396363 (Python Code)

Max Activating Token Index: 587

Text #15

Max Range: 4.0991. Min Range: -4.0991

Max Act: 1.6570. Min Act: -0.0000

Data Index: 1384482 (Python Code)

Max Activating Token Index: 875

Text #16

Max Range: 4.0991. Min Range: -4.0991

Max Act: 1.6614. Min Act: -0.0000

Data Index: 1487140 (Python Code)

Max Activating Token Index: 508

Text #17

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.0843. Min Act: -0.0000

Data Index: 1404383 (Python Code)

Max Activating Token Index: 963

Text #18

Max Range: 4.0991. Min Range: -4.0991

Max Act: 1.8432. Min Act: -0.0000

Data Index: 1502365 (Python Code)

Max Activating Token Index: 716

Text #19

Max Range: 4.0991. Min Range: -4.0991

Max Act: 1.8785. Min Act: -0.0000

Data Index: 1429422 (Python Code)

Max Activating Token Index: 805