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

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

Neuron 1491 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: 5.2734. Min Range: -5.2734

Max Act: 5.2734. Min Act: -0.1700

Data Index: 79946 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 5.2734. Min Range: -5.2734

Max Act: 5.1796. Min Act: -0.1700

Data Index: 357759 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 5.2734. Min Range: -5.2734

Max Act: 5.1640. Min Act: -0.1700

Data Index: 747120 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 5.2734. Min Range: -5.2734

Max Act: 5.1952. Min Act: -0.1700

Data Index: 1078596 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 5.2734. Min Range: -5.2734

Max Act: 5.0859. Min Act: -0.1700

Data Index: 960230 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 5.2734. Min Range: -5.2734

Max Act: 5.0546. Min Act: -0.1700

Data Index: 167785 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 5.2734. Min Range: -5.2734

Max Act: 5.1171. Min Act: -0.1700

Data Index: 236993 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 5.2734. Min Range: -5.2734

Max Act: 5.0859. Min Act: -0.1700

Data Index: 215518 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 5.2734. Min Range: -5.2734

Max Act: 5.0390. Min Act: -0.1700

Data Index: 300150 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 5.2734. Min Range: -5.2734

Max Act: 4.9296. Min Act: -0.1700

Data Index: 468388 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 5.2734. Min Range: -5.2734

Max Act: 5.0077. Min Act: -0.1700

Data Index: 449017 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 5.2734. Min Range: -5.2734

Max Act: 4.9765. Min Act: -0.1700

Data Index: 1327073 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 5.2734. Min Range: -5.2734

Max Act: 5.0702. Min Act: -0.1700

Data Index: 559685 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 5.2734. Min Range: -5.2734

Max Act: 5.0077. Min Act: -0.1700

Data Index: 1088491 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 5.2734. Min Range: -5.2734

Max Act: 5.0234. Min Act: -0.1700

Data Index: 283383 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 5.2734. Min Range: -5.2734

Max Act: 5.0859. Min Act: -0.1700

Data Index: 278688 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 5.2734. Min Range: -5.2734

Max Act: 4.9296. Min Act: -0.1700

Data Index: 1099587 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 5.2734. Min Range: -5.2734

Max Act: 4.9765. Min Act: -0.1700

Data Index: 1333214 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 5.2734. Min Range: -5.2734

Max Act: 4.9921. Min Act: -0.1700

Data Index: 921861 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 5.2734. Min Range: -5.2734

Max Act: 4.9140. Min Act: -0.1700

Data Index: 950545 (C4 (Web Text))

Max Activating Token Index: 441