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

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

Neuron 83 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.9003. Min Act: -0.1700

Data Index: 516680 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.9316. Min Act: -0.1700

Data Index: 192024 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.8377. Min Act: -0.1700

Data Index: 352479 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.8065. Min Act: -0.1700

Data Index: 670443 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.8065. Min Act: -0.1700

Data Index: 527397 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.8065. Min Act: -0.1700

Data Index: 1220703 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.7439. Min Act: -0.1700

Data Index: 905875 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.8065. Min Act: -0.1700

Data Index: 1210147 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.7439. Min Act: -0.1700

Data Index: 459092 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.7126. Min Act: -0.1700

Data Index: 587918 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.7752. Min Act: -0.1700

Data Index: 1302154 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.7126. Min Act: -0.1700

Data Index: 869561 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.7126. Min Act: -0.1700

Data Index: 232275 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.7439. Min Act: -0.1700

Data Index: 367794 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.7126. Min Act: -0.1700

Data Index: 479038 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.7126. Min Act: -0.1700

Data Index: 1190591 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.6813. Min Act: -0.1700

Data Index: 180268 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.7126. Min Act: -0.1700

Data Index: 1032192 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.7439. Min Act: -0.1700

Data Index: 327862 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 3.9316. Min Range: -3.9316

Max Act: 3.7439. Min Act: -0.1700

Data Index: 692278 (C4 (Web Text))

Max Activating Token Index: 968