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

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

Neuron 498 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: 2.4687. Min Range: -2.4687

Max Act: 2.4687. Min Act: 0.0001

Data Index: 1633573 (Python Code)

Max Activating Token Index: 675

Text #1

Max Range: 2.4687. Min Range: -2.4687

Max Act: 2.0403. Min Act: 0.0000

Data Index: 1454605 (Python Code)

Max Activating Token Index: 654

Text #2

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.6304. Min Act: -0.0000

Data Index: 1362283 (Python Code)

Max Activating Token Index: 774

Text #3

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.5547. Min Act: -0.0000

Data Index: 1490701 (Python Code)

Max Activating Token Index: 313

Text #4

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.4499. Min Act: -0.0000

Data Index: 1529940 (Python Code)

Max Activating Token Index: 192

Text #5

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.3381. Min Act: -0.0000

Data Index: 1367820 (Python Code)

Max Activating Token Index: 1021

Text #6

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.3812. Min Act: -0.0000

Data Index: 1444131 (Python Code)

Max Activating Token Index: 205

Text #7

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.1689. Min Act: -0.0000

Data Index: 1372089 (Python Code)

Max Activating Token Index: 658

Text #8

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.2071. Min Act: -0.0000

Data Index: 1495616 (Python Code)

Max Activating Token Index: 98

Text #9

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.1293. Min Act: -0.0000

Data Index: 1552301 (Python Code)

Max Activating Token Index: 82

Text #10

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.1990. Min Act: -0.0000

Data Index: 1381432 (Python Code)

Max Activating Token Index: 943

Text #11

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.1862. Min Act: -0.0000

Data Index: 1513434 (Python Code)

Max Activating Token Index: 350

Text #12

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.2238. Min Act: -0.0000

Data Index: 1559729 (Python Code)

Max Activating Token Index: 785

Text #13

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.1306. Min Act: -0.0000

Data Index: 1475709 (Python Code)

Max Activating Token Index: 155

Text #14

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.1598. Min Act: -0.0000

Data Index: 1565563 (Python Code)

Max Activating Token Index: 967

Text #15

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.1045. Min Act: -0.0000

Data Index: 1595823 (Python Code)

Max Activating Token Index: 1019

Text #16

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.1643. Min Act: 0.0000

Data Index: 1399013 (Python Code)

Max Activating Token Index: 437

Text #17

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1546905 (Python Code)

Max Activating Token Index: 516

Text #18

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1455789 (Python Code)

Max Activating Token Index: 464

Text #19

Max Range: 2.4687. Min Range: -2.4687

Max Act: 1.1893. Min Act: -0.0000

Data Index: 1492220 (Python Code)

Max Activating Token Index: 360