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

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

Neuron 231 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.2896. Min Act: -0.1700

Data Index: 234215 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.3521. Min Act: -0.1700

Data Index: 879133 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.3521. Min Act: -0.1700

Data Index: 225658 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.2583. Min Act: -0.1700

Data Index: 1209542 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.2896. Min Act: -0.1700

Data Index: 1050925 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.2583. Min Act: -0.1700

Data Index: 152560 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.2271. Min Act: -0.1700

Data Index: 346614 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.1958. Min Act: -0.1700

Data Index: 1233587 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.2271. Min Act: -0.1700

Data Index: 1043514 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.1958. Min Act: -0.1700

Data Index: 568232 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.1958. Min Act: -0.1700

Data Index: 721602 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.1958. Min Act: -0.1700

Data Index: 616634 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.1646. Min Act: -0.1700

Data Index: 577026 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.1333. Min Act: -0.1700

Data Index: 254479 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.0708. Min Act: -0.1700

Data Index: 758287 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.0708. Min Act: -0.1700

Data Index: 973675 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.1021. Min Act: -0.1700

Data Index: 747392 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.0396. Min Act: -0.1700

Data Index: 1003116 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.0708. Min Act: -0.1700

Data Index: 831945 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 5.3521. Min Range: -5.3521

Max Act: 5.1333. Min Act: -0.1700

Data Index: 59698 (C4 (Web Text))

Max Activating Token Index: 67