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

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

Neuron 1955 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: 7.8400. Min Range: -7.8400

Max Act: 7.8400. Min Act: -0.1700

Data Index: 1463596 (Python Code)

Max Activating Token Index: 991

Text #1

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.5900. Min Act: -0.1700

Data Index: 1411502 (Python Code)

Max Activating Token Index: 438

Text #2

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.5900. Min Act: -0.1700

Data Index: 1647477 (Python Code)

Max Activating Token Index: 986

Text #3

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.5275. Min Act: -0.1700

Data Index: 1483939 (Python Code)

Max Activating Token Index: 919

Text #4

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.4650. Min Act: -0.1700

Data Index: 1469343 (Python Code)

Max Activating Token Index: 774

Text #5

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.4025. Min Act: -0.1700

Data Index: 1497228 (Python Code)

Max Activating Token Index: 905

Text #6

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.4025. Min Act: -0.1700

Data Index: 1440623 (Python Code)

Max Activating Token Index: 868

Text #7

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.5275. Min Act: -0.1700

Data Index: 1505853 (Python Code)

Max Activating Token Index: 378

Text #8

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.4650. Min Act: -0.1700

Data Index: 1389446 (Python Code)

Max Activating Token Index: 736

Text #9

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.4650. Min Act: -0.1700

Data Index: 1591318 (Python Code)

Max Activating Token Index: 976

Text #10

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.3400. Min Act: -0.1700

Data Index: 1635886 (Python Code)

Max Activating Token Index: 611

Text #11

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.4025. Min Act: -0.1700

Data Index: 1454541 (Python Code)

Max Activating Token Index: 863

Text #12

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.4025. Min Act: -0.1700

Data Index: 1505596 (Python Code)

Max Activating Token Index: 981

Text #13

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.4025. Min Act: -0.1700

Data Index: 1538138 (Python Code)

Max Activating Token Index: 766

Text #14

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.4025. Min Act: -0.1700

Data Index: 1508203 (Python Code)

Max Activating Token Index: 1019

Text #15

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.3400. Min Act: -0.1700

Data Index: 1367634 (Python Code)

Max Activating Token Index: 928

Text #16

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.3400. Min Act: -0.1700

Data Index: 1425169 (Python Code)

Max Activating Token Index: 376

Text #17

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.3400. Min Act: -0.1700

Data Index: 1367553 (Python Code)

Max Activating Token Index: 689

Text #18

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.3400. Min Act: -0.1700

Data Index: 1625367 (Python Code)

Max Activating Token Index: 860

Text #19

Max Range: 7.8400. Min Range: -7.8400

Max Act: 7.3400. Min Act: -0.1700

Data Index: 1483614 (Python Code)

Max Activating Token Index: 958