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

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

Neuron 564 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: 5.3466. Min Range: -5.3466

Max Act: 5.3466. Min Act: -0.1700

Data Index: 459983 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 5.3466. Min Range: -5.3466

Max Act: 5.2841. Min Act: -0.1700

Data Index: 66158 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 5.3466. Min Range: -5.3466

Max Act: 5.1591. Min Act: -0.1700

Data Index: 801267 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 5.3466. Min Range: -5.3466

Max Act: 5.0341. Min Act: -0.1700

Data Index: 826372 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 5.3466. Min Range: -5.3466

Max Act: 5.0654. Min Act: -0.1700

Data Index: 499627 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 5.3466. Min Range: -5.3466

Max Act: 5.0654. Min Act: -0.1700

Data Index: 1242861 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 5.3466. Min Range: -5.3466

Max Act: 5.0654. Min Act: -0.1700

Data Index: 571998 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 5.3466. Min Range: -5.3466

Max Act: 5.0029. Min Act: -0.1700

Data Index: 164581 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 5.3466. Min Range: -5.3466

Max Act: 5.0341. Min Act: -0.1700

Data Index: 299479 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 5.3466. Min Range: -5.3466

Max Act: 5.0341. Min Act: -0.1700

Data Index: 724041 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 5.3466. Min Range: -5.3466

Max Act: 5.0029. Min Act: -0.1700

Data Index: 1162661 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 5.3466. Min Range: -5.3466

Max Act: 5.0029. Min Act: -0.1700

Data Index: 959628 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 5.3466. Min Range: -5.3466

Max Act: 5.0029. Min Act: -0.1700

Data Index: 1136532 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 5.3466. Min Range: -5.3466

Max Act: 5.0341. Min Act: -0.1700

Data Index: 157931 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 5.3466. Min Range: -5.3466

Max Act: 4.9716. Min Act: -0.1700

Data Index: 186068 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 5.3466. Min Range: -5.3466

Max Act: 5.0029. Min Act: -0.1700

Data Index: 915957 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 5.3466. Min Range: -5.3466

Max Act: 5.0029. Min Act: -0.1700

Data Index: 765691 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 5.3466. Min Range: -5.3466

Max Act: 4.9404. Min Act: -0.1700

Data Index: 34110 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 5.3466. Min Range: -5.3466

Max Act: 4.9716. Min Act: -0.1700

Data Index: 209313 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 5.3466. Min Range: -5.3466

Max Act: 5.0029. Min Act: -0.1700

Data Index: 546577 (C4 (Web Text))

Max Activating Token Index: 878