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

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

Neuron 1521 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0859. Min Range: -3.0859

Max Act: 3.0859. Min Act: -0.1700

Data Index: 1400614 (Python Code)

Max Activating Token Index: 54

Text #1

Max Range: 3.0859. Min Range: -3.0859

Max Act: 3.0543. Min Act: -0.1700

Data Index: 1080002 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 3.0859. Min Range: -3.0859

Max Act: 3.0701. Min Act: -0.1700

Data Index: 62722 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 3.0859. Min Range: -3.0859

Max Act: 3.0385. Min Act: -0.1700

Data Index: 487985 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 3.0859. Min Range: -3.0859

Max Act: 3.0227. Min Act: -0.1700

Data Index: 150697 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 3.0859. Min Range: -3.0859

Max Act: 3.0227. Min Act: -0.1700

Data Index: 1285848 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 3.0859. Min Range: -3.0859

Max Act: 3.0069. Min Act: -0.1700

Data Index: 1611629 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 3.0859. Min Range: -3.0859

Max Act: 2.9911. Min Act: -0.1700

Data Index: 512999 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 3.0859. Min Range: -3.0859

Max Act: 2.9595. Min Act: -0.1700

Data Index: 221984 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 3.0859. Min Range: -3.0859

Max Act: 2.9753. Min Act: -0.1700

Data Index: 584445 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 3.0859. Min Range: -3.0859

Max Act: 2.9753. Min Act: -0.1700

Data Index: 60387 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 3.0859. Min Range: -3.0859

Max Act: 2.9278. Min Act: -0.1700

Data Index: 685037 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 3.0859. Min Range: -3.0859

Max Act: 2.9436. Min Act: -0.1700

Data Index: 523046 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 3.0859. Min Range: -3.0859

Max Act: 2.9278. Min Act: -0.1700

Data Index: 700593 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 3.0859. Min Range: -3.0859

Max Act: 2.9436. Min Act: -0.1700

Data Index: 860797 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 3.0859. Min Range: -3.0859

Max Act: 2.9278. Min Act: -0.1700

Data Index: 75658 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 3.0859. Min Range: -3.0859

Max Act: 2.9595. Min Act: -0.1700

Data Index: 993142 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 3.0859. Min Range: -3.0859

Max Act: 2.9436. Min Act: -0.1700

Data Index: 1017541 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 3.0859. Min Range: -3.0859

Max Act: 2.9436. Min Act: -0.1700

Data Index: 964009 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 3.0859. Min Range: -3.0859

Max Act: 2.9436. Min Act: -0.1700

Data Index: 231569 (C4 (Web Text))

Max Activating Token Index: 34