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

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

Neuron 653 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: 3.9566. Min Range: -3.9566

Max Act: 3.9566. Min Act: -0.1700

Data Index: 1386826 (Python Code)

Max Activating Token Index: 17

Text #1

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.8315. Min Act: -0.1700

Data Index: 1602841 (Python Code)

Max Activating Token Index: 1011

Text #2

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.8940. Min Act: -0.1700

Data Index: 1496653 (Python Code)

Max Activating Token Index: 845

Text #3

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.8002. Min Act: -0.1700

Data Index: 1456797 (Python Code)

Max Activating Token Index: 905

Text #4

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.8002. Min Act: -0.1700

Data Index: 1585530 (Python Code)

Max Activating Token Index: 629

Text #5

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.7376. Min Act: -0.1700

Data Index: 1633494 (Python Code)

Max Activating Token Index: 695

Text #6

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.8002. Min Act: -0.1700

Data Index: 1515163 (Python Code)

Max Activating Token Index: 86

Text #7

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.7376. Min Act: -0.1700

Data Index: 1566818 (Python Code)

Max Activating Token Index: 989

Text #8

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.7689. Min Act: -0.1700

Data Index: 1473012 (Python Code)

Max Activating Token Index: 879

Text #9

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.7689. Min Act: -0.1700

Data Index: 1454586 (Python Code)

Max Activating Token Index: 868

Text #10

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.7689. Min Act: -0.1700

Data Index: 1505351 (Python Code)

Max Activating Token Index: 218

Text #11

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.7689. Min Act: -0.1700

Data Index: 1450762 (Python Code)

Max Activating Token Index: 864

Text #12

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.7376. Min Act: -0.1700

Data Index: 1526022 (Python Code)

Max Activating Token Index: 96

Text #13

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.7063. Min Act: -0.1700

Data Index: 1656136 (Python Code)

Max Activating Token Index: 161

Text #14

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.7376. Min Act: -0.1700

Data Index: 1566834 (Python Code)

Max Activating Token Index: 671

Text #15

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.7376. Min Act: -0.1700

Data Index: 1649434 (Python Code)

Max Activating Token Index: 256

Text #16

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.7063. Min Act: -0.1700

Data Index: 1481002 (Python Code)

Max Activating Token Index: 925

Text #17

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.7063. Min Act: -0.1700

Data Index: 1611352 (Python Code)

Max Activating Token Index: 923

Text #18

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.6750. Min Act: -0.1700

Data Index: 1590181 (Python Code)

Max Activating Token Index: 267

Text #19

Max Range: 3.9566. Min Range: -3.9566

Max Act: 3.7063. Min Act: -0.1700

Data Index: 1376866 (Python Code)

Max Activating Token Index: 400