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

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

Neuron 641 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.5161. Min Act: -0.1700

Data Index: 1394952 (Python Code)

Max Activating Token Index: 174

Text #1

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.4849. Min Act: -0.1700

Data Index: 1512980 (Python Code)

Max Activating Token Index: 822

Text #2

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.4536. Min Act: -0.1700

Data Index: 1646403 (Python Code)

Max Activating Token Index: 475

Text #3

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.4224. Min Act: -0.1700

Data Index: 1417304 (Python Code)

Max Activating Token Index: 496

Text #4

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.4224. Min Act: -0.1700

Data Index: 1590210 (Python Code)

Max Activating Token Index: 443

Text #5

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.4224. Min Act: -0.1700

Data Index: 1443860 (Python Code)

Max Activating Token Index: 770

Text #6

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.3911. Min Act: -0.1700

Data Index: 1580658 (Python Code)

Max Activating Token Index: 909

Text #7

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.4224. Min Act: -0.1700

Data Index: 1361075 (Python Code)

Max Activating Token Index: 478

Text #8

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.4224. Min Act: -0.1700

Data Index: 1549044 (Python Code)

Max Activating Token Index: 408

Text #9

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.3599. Min Act: -0.1700

Data Index: 1399208 (Python Code)

Max Activating Token Index: 737

Text #10

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.3911. Min Act: -0.1700

Data Index: 1510201 (Python Code)

Max Activating Token Index: 664

Text #11

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.3599. Min Act: -0.1700

Data Index: 1512858 (Python Code)

Max Activating Token Index: 329

Text #12

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.3599. Min Act: -0.1700

Data Index: 1511110 (Python Code)

Max Activating Token Index: 42

Text #13

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.3599. Min Act: -0.1700

Data Index: 1484113 (Python Code)

Max Activating Token Index: 487

Text #14

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.3599. Min Act: -0.1700

Data Index: 1600836 (Python Code)

Max Activating Token Index: 660

Text #15

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.3599. Min Act: -0.1700

Data Index: 1415970 (Python Code)

Max Activating Token Index: 434

Text #16

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.2974. Min Act: -0.1700

Data Index: 1391675 (Python Code)

Max Activating Token Index: 663

Text #17

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.2974. Min Act: -0.1700

Data Index: 1390768 (Python Code)

Max Activating Token Index: 264

Text #18

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.2974. Min Act: -0.1700

Data Index: 1593966 (Python Code)

Max Activating Token Index: 337

Text #19

Max Range: 5.5161. Min Range: -5.5161

Max Act: 5.3286. Min Act: -0.1700

Data Index: 1521682 (Python Code)

Max Activating Token Index: 651