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

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

Neuron 1122 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2847. Min Act: -0.1700

Data Index: 1583456 (Python Code)

Max Activating Token Index: 611

Text #1

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.3004. Min Act: -0.1700

Data Index: 1523106 (Python Code)

Max Activating Token Index: 619

Text #2

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2533. Min Act: -0.1700

Data Index: 1529791 (Python Code)

Max Activating Token Index: 279

Text #3

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2847. Min Act: -0.1700

Data Index: 1408799 (Python Code)

Max Activating Token Index: 247

Text #4

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2847. Min Act: -0.1700

Data Index: 1610909 (Python Code)

Max Activating Token Index: 617

Text #5

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2533. Min Act: -0.1700

Data Index: 1624789 (Python Code)

Max Activating Token Index: 766

Text #6

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2690. Min Act: -0.1700

Data Index: 1535613 (Python Code)

Max Activating Token Index: 766

Text #7

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2847. Min Act: -0.1700

Data Index: 1446784 (Python Code)

Max Activating Token Index: 218

Text #8

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2376. Min Act: -0.1700

Data Index: 1644550 (Python Code)

Max Activating Token Index: 217

Text #9

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2218. Min Act: -0.1700

Data Index: 1624724 (Python Code)

Max Activating Token Index: 289

Text #10

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2376. Min Act: -0.1700

Data Index: 1393187 (Python Code)

Max Activating Token Index: 582

Text #11

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2218. Min Act: -0.1700

Data Index: 1553075 (Python Code)

Max Activating Token Index: 70

Text #12

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2690. Min Act: -0.1700

Data Index: 1475269 (Python Code)

Max Activating Token Index: 346

Text #13

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.1904. Min Act: -0.1700

Data Index: 1611202 (Python Code)

Max Activating Token Index: 478

Text #14

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2061. Min Act: -0.1700

Data Index: 1480545 (Python Code)

Max Activating Token Index: 306

Text #15

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2061. Min Act: -0.1700

Data Index: 1406838 (Python Code)

Max Activating Token Index: 651

Text #16

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2061. Min Act: -0.1700

Data Index: 1569235 (Python Code)

Max Activating Token Index: 357

Text #17

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2061. Min Act: -0.1700

Data Index: 1544284 (Python Code)

Max Activating Token Index: 97

Text #18

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.1746. Min Act: -0.1700

Data Index: 1516351 (Python Code)

Max Activating Token Index: 352

Text #19

Max Range: 3.3004. Min Range: -3.3004

Max Act: 3.2218. Min Act: -0.1700

Data Index: 1395623 (Python Code)

Max Activating Token Index: 521