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

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

Neuron 717 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: 3.9014. Min Range: -3.9014

Max Act: 3.9014. Min Act: -0.1700

Data Index: 1337163 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.8076. Min Act: -0.1700

Data Index: 183874 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.8076. Min Act: -0.1700

Data Index: 1280456 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.7763. Min Act: -0.1700

Data Index: 365359 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.7763. Min Act: -0.1700

Data Index: 1297999 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.7763. Min Act: -0.1700

Data Index: 942688 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.7763. Min Act: -0.1700

Data Index: 902942 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.8389. Min Act: -0.1700

Data Index: 6168 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.7763. Min Act: -0.1700

Data Index: 1021223 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.8076. Min Act: -0.1700

Data Index: 367924 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.7450. Min Act: -0.1700

Data Index: 213842 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.7763. Min Act: -0.1700

Data Index: 631891 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.7450. Min Act: -0.1700

Data Index: 1323194 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.7450. Min Act: -0.1700

Data Index: 59908 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.8076. Min Act: -0.1700

Data Index: 677112 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.7450. Min Act: -0.1700

Data Index: 892239 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.7450. Min Act: -0.1700

Data Index: 1210655 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.7763. Min Act: -0.1700

Data Index: 976791 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.7450. Min Act: -0.1700

Data Index: 278217 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 3.9014. Min Range: -3.9014

Max Act: 3.7450. Min Act: -0.1700

Data Index: 375688 (C4 (Web Text))

Max Activating Token Index: 573