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

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

Neuron 1077 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: 7.1300. Min Range: -7.1300

Max Act: 7.1300. Min Act: -0.1700

Data Index: 1618879 (Python Code)

Max Activating Token Index: 468

Text #1

Max Range: 7.1300. Min Range: -7.1300

Max Act: 7.1300. Min Act: -0.1700

Data Index: 1449149 (Python Code)

Max Activating Token Index: 711

Text #2

Max Range: 7.1300. Min Range: -7.1300

Max Act: 7.0675. Min Act: -0.1695

Data Index: 1482790 (Python Code)

Max Activating Token Index: 992

Text #3

Max Range: 7.1300. Min Range: -7.1300

Max Act: 7.0675. Min Act: -0.1699

Data Index: 1400805 (Python Code)

Max Activating Token Index: 732

Text #4

Max Range: 7.1300. Min Range: -7.1300

Max Act: 7.1300. Min Act: -0.1700

Data Index: 1545185 (Python Code)

Max Activating Token Index: 371

Text #5

Max Range: 7.1300. Min Range: -7.1300

Max Act: 7.0050. Min Act: -0.1700

Data Index: 1415374 (Python Code)

Max Activating Token Index: 443

Text #6

Max Range: 7.1300. Min Range: -7.1300

Max Act: 6.9425. Min Act: -0.1700

Data Index: 1393820 (Python Code)

Max Activating Token Index: 457

Text #7

Max Range: 7.1300. Min Range: -7.1300

Max Act: 7.0050. Min Act: -0.1700

Data Index: 1497263 (Python Code)

Max Activating Token Index: 559

Text #8

Max Range: 7.1300. Min Range: -7.1300

Max Act: 7.0050. Min Act: -0.1700

Data Index: 1475108 (Python Code)

Max Activating Token Index: 993

Text #9

Max Range: 7.1300. Min Range: -7.1300

Max Act: 7.0050. Min Act: -0.1700

Data Index: 1627492 (Python Code)

Max Activating Token Index: 261

Text #10

Max Range: 7.1300. Min Range: -7.1300

Max Act: 6.9425. Min Act: -0.1700

Data Index: 1480712 (Python Code)

Max Activating Token Index: 115

Text #11

Max Range: 7.1300. Min Range: -7.1300

Max Act: 6.8175. Min Act: -0.1699

Data Index: 1591510 (Python Code)

Max Activating Token Index: 210

Text #12

Max Range: 7.1300. Min Range: -7.1300

Max Act: 6.8800. Min Act: -0.1700

Data Index: 1474095 (Python Code)

Max Activating Token Index: 873

Text #13

Max Range: 7.1300. Min Range: -7.1300

Max Act: 6.9425. Min Act: -0.1700

Data Index: 1643704 (Python Code)

Max Activating Token Index: 75

Text #14

Max Range: 7.1300. Min Range: -7.1300

Max Act: 6.8800. Min Act: -0.1699

Data Index: 1464402 (Python Code)

Max Activating Token Index: 604

Text #15

Max Range: 7.1300. Min Range: -7.1300

Max Act: 6.8175. Min Act: -0.1700

Data Index: 1520453 (Python Code)

Max Activating Token Index: 340

Text #16

Max Range: 7.1300. Min Range: -7.1300

Max Act: 6.7550. Min Act: -0.1699

Data Index: 1369913 (Python Code)

Max Activating Token Index: 957

Text #17

Max Range: 7.1300. Min Range: -7.1300

Max Act: 6.8175. Min Act: -0.1700

Data Index: 1568999 (Python Code)

Max Activating Token Index: 653

Text #18

Max Range: 7.1300. Min Range: -7.1300

Max Act: 6.8800. Min Act: -0.1700

Data Index: 1447240 (Python Code)

Max Activating Token Index: 581

Text #19

Max Range: 7.1300. Min Range: -7.1300

Max Act: 6.7550. Min Act: -0.1699

Data Index: 1415619 (Python Code)

Max Activating Token Index: 859