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

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

Neuron 1638 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2687. Min Range: -5.2687

Max Act: 5.2687. Min Act: -0.1700

Data Index: 788941 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 5.2687. Min Range: -5.2687

Max Act: 5.2375. Min Act: -0.1700

Data Index: 690593 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 5.2687. Min Range: -5.2687

Max Act: 5.1437. Min Act: -0.1700

Data Index: 1146430 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 5.2687. Min Range: -5.2687

Max Act: 5.1437. Min Act: -0.1700

Data Index: 408273 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 5.2687. Min Range: -5.2687

Max Act: 5.2062. Min Act: -0.1700

Data Index: 554100 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 5.2687. Min Range: -5.2687

Max Act: 5.1125. Min Act: -0.1700

Data Index: 660855 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 5.2687. Min Range: -5.2687

Max Act: 5.0812. Min Act: -0.1700

Data Index: 187503 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 5.2687. Min Range: -5.2687

Max Act: 5.1125. Min Act: -0.1700

Data Index: 421119 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 5.2687. Min Range: -5.2687

Max Act: 5.0500. Min Act: -0.1700

Data Index: 1147985 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 5.2687. Min Range: -5.2687

Max Act: 5.0812. Min Act: -0.1700

Data Index: 603497 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 5.2687. Min Range: -5.2687

Max Act: 5.1125. Min Act: -0.1700

Data Index: 314610 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 5.2687. Min Range: -5.2687

Max Act: 5.0812. Min Act: -0.1700

Data Index: 579657 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 5.2687. Min Range: -5.2687

Max Act: 5.0812. Min Act: -0.1700

Data Index: 103409 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 5.2687. Min Range: -5.2687

Max Act: 4.9875. Min Act: -0.1700

Data Index: 644984 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 5.2687. Min Range: -5.2687

Max Act: 4.9875. Min Act: -0.1700

Data Index: 517412 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 5.2687. Min Range: -5.2687

Max Act: 4.9562. Min Act: -0.1700

Data Index: 734697 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 5.2687. Min Range: -5.2687

Max Act: 4.9562. Min Act: -0.1700

Data Index: 456489 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 5.2687. Min Range: -5.2687

Max Act: 4.8625. Min Act: -0.1700

Data Index: 307201 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 5.2687. Min Range: -5.2687

Max Act: 4.8625. Min Act: -0.1700

Data Index: 918382 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 5.2687. Min Range: -5.2687

Max Act: 4.8000. Min Act: -0.1700

Data Index: 857841 (C4 (Web Text))

Max Activating Token Index: 859