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

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

Neuron 1464 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: 9.2984. Min Range: -9.2984

Max Act: 9.2984. Min Act: -0.1700

Data Index: 1644658 (Python Code)

Max Activating Token Index: 308

Text #1

Max Range: 9.2984. Min Range: -9.2984

Max Act: 9.1734. Min Act: -0.1700

Data Index: 1648084 (Python Code)

Max Activating Token Index: 606

Text #2

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.9234. Min Act: -0.1700

Data Index: 1431887 (Python Code)

Max Activating Token Index: 884

Text #3

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.7984. Min Act: -0.1700

Data Index: 1504742 (Python Code)

Max Activating Token Index: 703

Text #4

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.6734. Min Act: -0.1700

Data Index: 1464289 (Python Code)

Max Activating Token Index: 579

Text #5

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.6109. Min Act: -0.1700

Data Index: 1616440 (Python Code)

Max Activating Token Index: 222

Text #6

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.3609. Min Act: -0.1700

Data Index: 1368942 (Python Code)

Max Activating Token Index: 558

Text #7

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.3609. Min Act: -0.1700

Data Index: 1400311 (Python Code)

Max Activating Token Index: 413

Text #8

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.3609. Min Act: -0.1700

Data Index: 1592397 (Python Code)

Max Activating Token Index: 477

Text #9

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.2359. Min Act: -0.1700

Data Index: 1562731 (Python Code)

Max Activating Token Index: 301

Text #10

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.3609. Min Act: -0.1700

Data Index: 1438543 (Python Code)

Max Activating Token Index: 228

Text #11

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.2984. Min Act: -0.1700

Data Index: 1423207 (Python Code)

Max Activating Token Index: 1021

Text #12

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.2984. Min Act: -0.1700

Data Index: 1568741 (Python Code)

Max Activating Token Index: 524

Text #13

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.3609. Min Act: -0.1700

Data Index: 1417497 (Python Code)

Max Activating Token Index: 753

Text #14

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.4234. Min Act: -0.1700

Data Index: 1388744 (Python Code)

Max Activating Token Index: 778

Text #15

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.3609. Min Act: -0.1700

Data Index: 1501770 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.3609. Min Act: -0.1700

Data Index: 1599568 (Python Code)

Max Activating Token Index: 807

Text #17

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.2984. Min Act: -0.1700

Data Index: 1606991 (Python Code)

Max Activating Token Index: 335

Text #18

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.2984. Min Act: -0.1700

Data Index: 1613592 (Python Code)

Max Activating Token Index: 426

Text #19

Max Range: 9.2984. Min Range: -9.2984

Max Act: 8.2984. Min Act: -0.1700

Data Index: 1437234 (Python Code)

Max Activating Token Index: 140