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

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

Neuron 577 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.8949. Min Act: -0.1700

Data Index: 739514 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.8636. Min Act: -0.1700

Data Index: 302541 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.8636. Min Act: -0.1700

Data Index: 1253553 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.8324. Min Act: -0.1700

Data Index: 1284579 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.8011. Min Act: -0.1700

Data Index: 1095560 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.8011. Min Act: -0.1700

Data Index: 889241 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.8011. Min Act: -0.1700

Data Index: 428131 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.8011. Min Act: -0.1700

Data Index: 324083 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.7698. Min Act: -0.1700

Data Index: 873212 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.7385. Min Act: -0.1700

Data Index: 423371 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.7698. Min Act: -0.1700

Data Index: 1237890 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.7698. Min Act: -0.1700

Data Index: 1204819 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.7385. Min Act: -0.1700

Data Index: 364012 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.7385. Min Act: -0.1700

Data Index: 1188517 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.7385. Min Act: -0.1700

Data Index: 338013 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.7385. Min Act: -0.1700

Data Index: 681280 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.7385. Min Act: -0.1700

Data Index: 214863 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.7072. Min Act: -0.1700

Data Index: 1189780 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.7385. Min Act: -0.1700

Data Index: 1100921 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 3.8949. Min Range: -3.8949

Max Act: 3.7385. Min Act: -0.1700

Data Index: 780571 (C4 (Web Text))

Max Activating Token Index: 957