Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1539 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.1220. Min Range: -5.1220

Max Act: 5.1220. Min Act: -0.1698

Data Index: 1642633 (Python Code)

Max Activating Token Index: 273

Text #1

Max Range: 5.1220. Min Range: -5.1220

Max Act: 5.1220. Min Act: -0.1700

Data Index: 121167 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 5.1220. Min Range: -5.1220

Max Act: 5.1220. Min Act: -0.1700

Data Index: 1452520 (Python Code)

Max Activating Token Index: 573

Text #3

Max Range: 5.1220. Min Range: -5.1220

Max Act: 5.0282. Min Act: -0.1700

Data Index: 1452445 (Python Code)

Max Activating Token Index: 380

Text #4

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.9657. Min Act: -0.1699

Data Index: 234679 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.9032. Min Act: -0.1698

Data Index: 1361688 (Python Code)

Max Activating Token Index: 373

Text #6

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.8720. Min Act: -0.1698

Data Index: 1472057 (Python Code)

Max Activating Token Index: 882

Text #7

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.8720. Min Act: -0.1700

Data Index: 1520162 (Python Code)

Max Activating Token Index: 110

Text #8

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.8720. Min Act: -0.1615

Data Index: 1395409 (Python Code)

Max Activating Token Index: 262

Text #9

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.8407. Min Act: -0.1700

Data Index: 1633365 (Python Code)

Max Activating Token Index: 544

Text #10

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.7470. Min Act: -0.1700

Data Index: 1531299 (Python Code)

Max Activating Token Index: 836

Text #11

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.7782. Min Act: -0.1700

Data Index: 1575685 (Python Code)

Max Activating Token Index: 479

Text #12

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.7470. Min Act: -0.1700

Data Index: 1429232 (Python Code)

Max Activating Token Index: 550

Text #13

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.8095. Min Act: -0.1700

Data Index: 1641072 (Python Code)

Max Activating Token Index: 1007

Text #14

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.7157. Min Act: -0.1700

Data Index: 1500136 (Python Code)

Max Activating Token Index: 116

Text #15

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.7782. Min Act: -0.1700

Data Index: 1521771 (Python Code)

Max Activating Token Index: 830

Text #16

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.7782. Min Act: -0.1700

Data Index: 733694 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.7470. Min Act: -0.1699

Data Index: 1629036 (Python Code)

Max Activating Token Index: 533

Text #18

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.6845. Min Act: -0.1617

Data Index: 1479387 (Python Code)

Max Activating Token Index: 638

Text #19

Max Range: 5.1220. Min Range: -5.1220

Max Act: 4.7470. Min Act: -0.1700

Data Index: 1395104 (Python Code)

Max Activating Token Index: 534