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

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

Neuron 5464 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: 2.4747. Min Range: -2.4747

Max Act: 2.4747. Min Act: -0.0000

Data Index: 1564761 (Python Code)

Max Activating Token Index: 624

Text #1

Max Range: 2.4747. Min Range: -2.4747

Max Act: 2.4451. Min Act: -0.0000

Data Index: 1560246 (Python Code)

Max Activating Token Index: 106

Text #2

Max Range: 2.4747. Min Range: -2.4747

Max Act: 2.4109. Min Act: -0.0000

Data Index: 1464018 (Python Code)

Max Activating Token Index: 809

Text #3

Max Range: 2.4747. Min Range: -2.4747

Max Act: 2.4607. Min Act: -0.0000

Data Index: 1583661 (Python Code)

Max Activating Token Index: 607

Text #4

Max Range: 2.4747. Min Range: -2.4747

Max Act: 2.4084. Min Act: -0.0000

Data Index: 1633458 (Python Code)

Max Activating Token Index: 913

Text #5

Max Range: 2.4747. Min Range: -2.4747

Max Act: 2.2522. Min Act: -0.0000

Data Index: 1649440 (Python Code)

Max Activating Token Index: 668

Text #6

Max Range: 2.4747. Min Range: -2.4747

Max Act: 2.2432. Min Act: -0.0000

Data Index: 1455877 (Python Code)

Max Activating Token Index: 305

Text #7

Max Range: 2.4747. Min Range: -2.4747

Max Act: 2.2751. Min Act: -0.0000

Data Index: 1550126 (Python Code)

Max Activating Token Index: 121

Text #8

Max Range: 2.4747. Min Range: -2.4747

Max Act: 2.1533. Min Act: -0.0000

Data Index: 1569365 (Python Code)

Max Activating Token Index: 691

Text #9

Max Range: 2.4747. Min Range: -2.4747

Max Act: 2.2452. Min Act: -0.0000

Data Index: 1544235 (Python Code)

Max Activating Token Index: 470

Text #10

Max Range: 2.4747. Min Range: -2.4747

Max Act: 2.0073. Min Act: -0.0000

Data Index: 1646586 (Python Code)

Max Activating Token Index: 51

Text #11

Max Range: 2.4747. Min Range: -2.4747

Max Act: 2.2221. Min Act: -0.0000

Data Index: 1601311 (Python Code)

Max Activating Token Index: 351

Text #12

Max Range: 2.4747. Min Range: -2.4747

Max Act: 2.1938. Min Act: -0.0000

Data Index: 1426059 (Python Code)

Max Activating Token Index: 253

Text #13

Max Range: 2.4747. Min Range: -2.4747

Max Act: 2.0450. Min Act: -0.0000

Data Index: 1396708 (Python Code)

Max Activating Token Index: 422

Text #14

Max Range: 2.4747. Min Range: -2.4747

Max Act: 2.0159. Min Act: -0.0000

Data Index: 1601547 (Python Code)

Max Activating Token Index: 654

Text #15

Max Range: 2.4747. Min Range: -2.4747

Max Act: 1.8296. Min Act: -0.0000

Data Index: 1645640 (Python Code)

Max Activating Token Index: 319

Text #16

Max Range: 2.4747. Min Range: -2.4747

Max Act: 1.9381. Min Act: -0.0000

Data Index: 1589778 (Python Code)

Max Activating Token Index: 1005

Text #17

Max Range: 2.4747. Min Range: -2.4747

Max Act: 1.9258. Min Act: -0.0000

Data Index: 1415629 (Python Code)

Max Activating Token Index: 814

Text #18

Max Range: 2.4747. Min Range: -2.4747

Max Act: 1.7456. Min Act: -0.0000

Data Index: 1421786 (Python Code)

Max Activating Token Index: 845

Text #19

Max Range: 2.4747. Min Range: -2.4747

Max Act: 1.8811. Min Act: -0.0000

Data Index: 1571219 (Python Code)

Max Activating Token Index: 952