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

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

Neuron 449 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.9041. Min Act: -0.1700

Data Index: 1655339 (Python Code)

Max Activating Token Index: 647

Text #1

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.8416. Min Act: -0.1700

Data Index: 31431 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.8416. Min Act: -0.1700

Data Index: 1387486 (Python Code)

Max Activating Token Index: 884

Text #3

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.7478. Min Act: -0.1700

Data Index: 1636224 (Python Code)

Max Activating Token Index: 820

Text #4

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.7165. Min Act: -0.1700

Data Index: 1502392 (Python Code)

Max Activating Token Index: 765

Text #5

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.6852. Min Act: -0.1700

Data Index: 1464191 (Python Code)

Max Activating Token Index: 755

Text #6

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.6539. Min Act: -0.1700

Data Index: 1635786 (Python Code)

Max Activating Token Index: 748

Text #7

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.6226. Min Act: -0.1700

Data Index: 1518661 (Python Code)

Max Activating Token Index: 260

Text #8

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.6226. Min Act: -0.1700

Data Index: 1536197 (Python Code)

Max Activating Token Index: 20

Text #9

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.6539. Min Act: -0.1700

Data Index: 1543081 (Python Code)

Max Activating Token Index: 657

Text #10

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.6539. Min Act: -0.1700

Data Index: 1554637 (Python Code)

Max Activating Token Index: 176

Text #11

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.6539. Min Act: -0.1700

Data Index: 1568524 (Python Code)

Max Activating Token Index: 763

Text #12

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.6539. Min Act: -0.1700

Data Index: 1615950 (Python Code)

Max Activating Token Index: 979

Text #13

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.6226. Min Act: -0.1700

Data Index: 1627852 (Python Code)

Max Activating Token Index: 217

Text #14

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.6226. Min Act: -0.1700

Data Index: 1463642 (Python Code)

Max Activating Token Index: 905

Text #15

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.6226. Min Act: -0.1700

Data Index: 1609283 (Python Code)

Max Activating Token Index: 195

Text #16

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.5912. Min Act: -0.1700

Data Index: 1603755 (Python Code)

Max Activating Token Index: 810

Text #17

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.6539. Min Act: -0.1700

Data Index: 1644506 (Python Code)

Max Activating Token Index: 895

Text #18

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.6226. Min Act: -0.1700

Data Index: 1385037 (Python Code)

Max Activating Token Index: 698

Text #19

Max Range: 3.9041. Min Range: -3.9041

Max Act: 3.5912. Min Act: -0.1700

Data Index: 1576918 (Python Code)

Max Activating Token Index: 317