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

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

Neuron 1739 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: 3.9702. Min Range: -3.9702

Max Act: 3.9702. Min Act: -0.1700

Data Index: 846196 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.8138. Min Act: -0.1700

Data Index: 298404 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.7825. Min Act: -0.1700

Data Index: 81940 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.7512. Min Act: -0.1700

Data Index: 934443 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.7200. Min Act: -0.1700

Data Index: 1606410 (Python Code)

Max Activating Token Index: 334

Text #5

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.7200. Min Act: -0.1700

Data Index: 1374508 (Python Code)

Max Activating Token Index: 64

Text #6

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.6887. Min Act: -0.1700

Data Index: 1344848 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.7200. Min Act: -0.1700

Data Index: 298954 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.6574. Min Act: -0.1700

Data Index: 957821 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.6887. Min Act: -0.1700

Data Index: 886254 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.6574. Min Act: -0.1700

Data Index: 336571 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.6574. Min Act: -0.1700

Data Index: 1552550 (Python Code)

Max Activating Token Index: 142

Text #12

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.6574. Min Act: -0.1700

Data Index: 1470090 (Python Code)

Max Activating Token Index: 674

Text #13

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.6574. Min Act: -0.1700

Data Index: 687047 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.6261. Min Act: -0.1700

Data Index: 174575 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.5947. Min Act: -0.1700

Data Index: 568714 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.6261. Min Act: -0.1700

Data Index: 1526230 (Python Code)

Max Activating Token Index: 329

Text #17

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.6261. Min Act: -0.1700

Data Index: 1513807 (Python Code)

Max Activating Token Index: 675

Text #18

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.5634. Min Act: -0.1700

Data Index: 1475306 (Python Code)

Max Activating Token Index: 323

Text #19

Max Range: 3.9702. Min Range: -3.9702

Max Act: 3.5947. Min Act: -0.1700

Data Index: 1034443 (C4 (Web Text))

Max Activating Token Index: 850