Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 61 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.2658. Min Act: -0.1700

Data Index: 1596210 (Python Code)

Max Activating Token Index: 1012

Text #1

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.2187. Min Act: -0.1700

Data Index: 1641919 (Python Code)

Max Activating Token Index: 1012

Text #2

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.2030. Min Act: -0.1700

Data Index: 1531544 (Python Code)

Max Activating Token Index: 412

Text #3

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.1715. Min Act: -0.1700

Data Index: 1395888 (Python Code)

Max Activating Token Index: 613

Text #4

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.1557. Min Act: -0.1700

Data Index: 1481857 (Python Code)

Max Activating Token Index: 458

Text #5

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.1557. Min Act: -0.1700

Data Index: 1592286 (Python Code)

Max Activating Token Index: 387

Text #6

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.1715. Min Act: -0.1700

Data Index: 1530252 (Python Code)

Max Activating Token Index: 261

Text #7

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.1400. Min Act: -0.1700

Data Index: 1470953 (Python Code)

Max Activating Token Index: 299

Text #8

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.1715. Min Act: -0.1700

Data Index: 1556390 (Python Code)

Max Activating Token Index: 520

Text #9

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.1715. Min Act: -0.1700

Data Index: 1590605 (Python Code)

Max Activating Token Index: 700

Text #10

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.1557. Min Act: -0.1700

Data Index: 1606563 (Python Code)

Max Activating Token Index: 259

Text #11

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.1400. Min Act: -0.1700

Data Index: 1645227 (Python Code)

Max Activating Token Index: 699

Text #12

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.1557. Min Act: -0.1700

Data Index: 1403442 (Python Code)

Max Activating Token Index: 279

Text #13

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.1400. Min Act: -0.1700

Data Index: 1460125 (Python Code)

Max Activating Token Index: 405

Text #14

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.1085. Min Act: -0.1700

Data Index: 1512358 (Python Code)

Max Activating Token Index: 346

Text #15

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.1557. Min Act: -0.1700

Data Index: 1510489 (Python Code)

Max Activating Token Index: 713

Text #16

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.1400. Min Act: -0.1700

Data Index: 1641190 (Python Code)

Max Activating Token Index: 974

Text #17

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.1242. Min Act: -0.1700

Data Index: 1597676 (Python Code)

Max Activating Token Index: 792

Text #18

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.1715. Min Act: -0.1700

Data Index: 1510299 (Python Code)

Max Activating Token Index: 815

Text #19

Max Range: 3.2658. Min Range: -3.2658

Max Act: 3.1242. Min Act: -0.1700

Data Index: 1474375 (Python Code)

Max Activating Token Index: 777