Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1660 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.8689. Min Act: -0.1700

Data Index: 545400 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.8533. Min Act: -0.1700

Data Index: 1215569 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.8377. Min Act: -0.1700

Data Index: 880145 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.8064. Min Act: -0.1700

Data Index: 559989 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.8064. Min Act: -0.1700

Data Index: 842799 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.8220. Min Act: -0.1700

Data Index: 831902 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.7751. Min Act: -0.1700

Data Index: 943521 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.7595. Min Act: -0.1700

Data Index: 577258 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.7595. Min Act: -0.1700

Data Index: 432096 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.7438. Min Act: -0.1700

Data Index: 518591 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.7751. Min Act: -0.1700

Data Index: 1355907 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.7438. Min Act: -0.1700

Data Index: 992922 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.7751. Min Act: -0.1700

Data Index: 1083382 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.7438. Min Act: -0.1700

Data Index: 137430 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.7751. Min Act: -0.1700

Data Index: 40943 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.7438. Min Act: -0.1700

Data Index: 784581 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.7438. Min Act: -0.1700

Data Index: 41466 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.7595. Min Act: -0.1700

Data Index: 395884 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.7595. Min Act: -0.1700

Data Index: 7871 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.7282. Min Act: -0.1700

Data Index: 525790 (C4 (Web Text))

Max Activating Token Index: 820