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

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

Neuron 1614 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2233. Min Range: -2.2233

Max Act: 2.2233. Min Act: -0.0000

Data Index: 1452558 (Python Code)

Max Activating Token Index: 732

Text #1

Max Range: 2.2233. Min Range: -2.2233

Max Act: 2.0996. Min Act: -0.0000

Data Index: 1387134 (Python Code)

Max Activating Token Index: 623

Text #2

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.8764. Min Act: -0.0000

Data Index: 1388919 (Python Code)

Max Activating Token Index: 152

Text #3

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.8602. Min Act: -0.0000

Data Index: 1486603 (Python Code)

Max Activating Token Index: 643

Text #4

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.6671. Min Act: -0.0000

Data Index: 1478736 (Python Code)

Max Activating Token Index: 814

Text #5

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.6998. Min Act: -0.0000

Data Index: 1367718 (Python Code)

Max Activating Token Index: 726

Text #6

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.5444. Min Act: -0.0000

Data Index: 1586236 (Python Code)

Max Activating Token Index: 586

Text #7

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.6103. Min Act: -0.0000

Data Index: 1549207 (Python Code)

Max Activating Token Index: 559

Text #8

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.5156. Min Act: -0.0000

Data Index: 1414456 (Python Code)

Max Activating Token Index: 299

Text #9

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.5922. Min Act: -0.0000

Data Index: 1393723 (Python Code)

Max Activating Token Index: 805

Text #10

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.5098. Min Act: -0.0000

Data Index: 1564591 (Python Code)

Max Activating Token Index: 285

Text #11

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.5810. Min Act: -0.0000

Data Index: 1613701 (Python Code)

Max Activating Token Index: 373

Text #12

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.4775. Min Act: -0.0000

Data Index: 1467762 (Python Code)

Max Activating Token Index: 940

Text #13

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.4751. Min Act: -0.0000

Data Index: 1418164 (Python Code)

Max Activating Token Index: 886

Text #14

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.4627. Min Act: -0.0000

Data Index: 1491986 (Python Code)

Max Activating Token Index: 639

Text #15

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.4472. Min Act: -0.0000

Data Index: 1631481 (Python Code)

Max Activating Token Index: 485

Text #16

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.8237. Min Act: -0.0000

Data Index: 1555625 (Python Code)

Max Activating Token Index: 998

Text #17

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.5080. Min Act: -0.0000

Data Index: 1490146 (Python Code)

Max Activating Token Index: 226

Text #18

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.5071. Min Act: -0.0000

Data Index: 1381997 (Python Code)

Max Activating Token Index: 320

Text #19

Max Range: 2.2233. Min Range: -2.2233

Max Act: 1.4891. Min Act: -0.0000

Data Index: 1464349 (Python Code)

Max Activating Token Index: 77