Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 960 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.2331. Min Act: -0.1700

Data Index: 1554541 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.1706. Min Act: -0.1700

Data Index: 1631523 (Python Code)

Max Activating Token Index: 288

Text #2

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.2019. Min Act: -0.1700

Data Index: 1482534 (Python Code)

Max Activating Token Index: 23

Text #3

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.2019. Min Act: -0.1700

Data Index: 1483106 (Python Code)

Max Activating Token Index: 756

Text #4

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.1706. Min Act: -0.1700

Data Index: 1476117 (Python Code)

Max Activating Token Index: 428

Text #5

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.2019. Min Act: -0.1700

Data Index: 1526175 (Python Code)

Max Activating Token Index: 768

Text #6

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.1081. Min Act: -0.1700

Data Index: 1380583 (Python Code)

Max Activating Token Index: 323

Text #7

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.2019. Min Act: -0.1700

Data Index: 1478271 (Python Code)

Max Activating Token Index: 393

Text #8

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.1706. Min Act: -0.1700

Data Index: 1459234 (Python Code)

Max Activating Token Index: 505

Text #9

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.1706. Min Act: -0.1700

Data Index: 1402178 (Python Code)

Max Activating Token Index: 389

Text #10

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.1394. Min Act: -0.1700

Data Index: 1375175 (Python Code)

Max Activating Token Index: 786

Text #11

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.1394. Min Act: -0.1700

Data Index: 1360890 (Python Code)

Max Activating Token Index: 602

Text #12

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.1394. Min Act: -0.1700

Data Index: 1381428 (Python Code)

Max Activating Token Index: 424

Text #13

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.1081. Min Act: -0.1700

Data Index: 1403469 (Python Code)

Max Activating Token Index: 444

Text #14

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.1394. Min Act: -0.1700

Data Index: 1523403 (Python Code)

Max Activating Token Index: 585

Text #15

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.1081. Min Act: -0.1700

Data Index: 1395132 (Python Code)

Max Activating Token Index: 437

Text #16

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.0769. Min Act: -0.1700

Data Index: 1502030 (Python Code)

Max Activating Token Index: 826

Text #17

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.1081. Min Act: -0.1700

Data Index: 1416714 (Python Code)

Max Activating Token Index: 562

Text #18

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.1081. Min Act: -0.1700

Data Index: 1496456 (Python Code)

Max Activating Token Index: 363

Text #19

Max Range: 5.2331. Min Range: -5.2331

Max Act: 5.0456. Min Act: -0.1700

Data Index: 1476697 (Python Code)

Max Activating Token Index: 478