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

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

Neuron 2019 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: 4.0029. Min Range: -4.0029

Max Act: 4.0029. Min Act: -0.1700

Data Index: 559189 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.9716. Min Act: -0.1700

Data Index: 882465 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.9403. Min Act: -0.1700

Data Index: 531252 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.9091. Min Act: -0.1700

Data Index: 1206751 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.9403. Min Act: -0.1700

Data Index: 818850 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.9091. Min Act: -0.1700

Data Index: 129453 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.9403. Min Act: -0.1700

Data Index: 291336 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.9716. Min Act: -0.1700

Data Index: 1345217 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.8778. Min Act: -0.1700

Data Index: 750467 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.9091. Min Act: -0.1700

Data Index: 681180 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.8465. Min Act: -0.1700

Data Index: 1243247 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.8465. Min Act: -0.1700

Data Index: 365614 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.8465. Min Act: -0.1700

Data Index: 110448 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.7996. Min Act: -0.1700

Data Index: 367287 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.7683. Min Act: -0.1700

Data Index: 1093429 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.7839. Min Act: -0.1700

Data Index: 269358 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.7996. Min Act: -0.1700

Data Index: 832414 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.7839. Min Act: -0.1700

Data Index: 1206008 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.8152. Min Act: -0.1700

Data Index: 244631 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 4.0029. Min Range: -4.0029

Max Act: 3.7683. Min Act: -0.1700

Data Index: 500611 (C4 (Web Text))

Max Activating Token Index: 701