Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2412 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1296. Min Range: -1.1296

Max Act: 1.1296. Min Act: -0.0001

Data Index: 1485000 (Python Code)

Max Activating Token Index: 395

Text #1

Max Range: 1.1296. Min Range: -1.1296

Max Act: 1.0392. Min Act: -0.0001

Data Index: 1645234 (Python Code)

Max Activating Token Index: 829

Text #2

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.9905. Min Act: -0.0001

Data Index: 1558481 (Python Code)

Max Activating Token Index: 520

Text #3

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.9698. Min Act: -0.0001

Data Index: 1499042 (Python Code)

Max Activating Token Index: 62

Text #4

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.7982. Min Act: -0.0001

Data Index: 1621795 (Python Code)

Max Activating Token Index: 768

Text #5

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.9377. Min Act: -0.0001

Data Index: 1479863 (Python Code)

Max Activating Token Index: 297

Text #6

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.9669. Min Act: -0.0001

Data Index: 1603986 (Python Code)

Max Activating Token Index: 344

Text #7

Max Range: 1.1296. Min Range: -1.1296

Max Act: 1.0006. Min Act: -0.0001

Data Index: 1507029 (Python Code)

Max Activating Token Index: 637

Text #8

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8713. Min Act: -0.0001

Data Index: 1486360 (Python Code)

Max Activating Token Index: 444

Text #9

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.9032. Min Act: -0.0001

Data Index: 1397959 (Python Code)

Max Activating Token Index: 670

Text #10

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.7436. Min Act: -0.0001

Data Index: 1578515 (Python Code)

Max Activating Token Index: 681

Text #11

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8544. Min Act: -0.0001

Data Index: 1572050 (Python Code)

Max Activating Token Index: 693

Text #12

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8183. Min Act: -0.0001

Data Index: 1497421 (Python Code)

Max Activating Token Index: 279

Text #13

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8095. Min Act: -0.0001

Data Index: 1621985 (Python Code)

Max Activating Token Index: 310

Text #14

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.7478. Min Act: -0.0001

Data Index: 1452494 (Python Code)

Max Activating Token Index: 107

Text #15

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.6904. Min Act: -0.0001

Data Index: 1476550 (Python Code)

Max Activating Token Index: 744

Text #16

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8627. Min Act: -0.0001

Data Index: 1591978 (Python Code)

Max Activating Token Index: 929

Text #17

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.7728. Min Act: -0.0001

Data Index: 1491180 (Python Code)

Max Activating Token Index: 668

Text #18

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.7317. Min Act: -0.0001

Data Index: 1456187 (Python Code)

Max Activating Token Index: 379

Text #19

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.7545. Min Act: -0.0001

Data Index: 1553170 (Python Code)

Max Activating Token Index: 490