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

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

Neuron 6069 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: 0.6079. Min Range: -0.6079

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1462508 (Python Code)

Max Activating Token Index: 995

Text #1

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5641. Min Act: -0.0000

Data Index: 1633873 (Python Code)

Max Activating Token Index: 520

Text #2

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1576503 (Python Code)

Max Activating Token Index: 769

Text #3

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1633954 (Python Code)

Max Activating Token Index: 476

Text #4

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1389747 (Python Code)

Max Activating Token Index: 551

Text #5

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1450798 (Python Code)

Max Activating Token Index: 822

Text #6

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4983. Min Act: -0.0000

Data Index: 1443878 (Python Code)

Max Activating Token Index: 596

Text #7

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4874. Min Act: -0.0000

Data Index: 1439476 (Python Code)

Max Activating Token Index: 810

Text #8

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1458421 (Python Code)

Max Activating Token Index: 104

Text #9

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1425281 (Python Code)

Max Activating Token Index: 165

Text #10

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4473. Min Act: -0.0000

Data Index: 1539922 (Python Code)

Max Activating Token Index: 870

Text #11

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4551. Min Act: -0.0000

Data Index: 1526888 (Python Code)

Max Activating Token Index: 468

Text #12

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1491998 (Python Code)

Max Activating Token Index: 581

Text #13

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1595665 (Python Code)

Max Activating Token Index: 230

Text #14

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1560623 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1647101 (Python Code)

Max Activating Token Index: 593

Text #16

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4563. Min Act: -0.0000

Data Index: 1472310 (Python Code)

Max Activating Token Index: 83

Text #17

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1425328 (Python Code)

Max Activating Token Index: 876

Text #18

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1438856 (Python Code)

Max Activating Token Index: 387

Text #19

Max Range: 0.6079. Min Range: -0.6079

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1473362 (Python Code)

Max Activating Token Index: 650