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

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

Neuron 646 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: 3.4238. Min Range: -3.4238

Max Act: 3.3768. Min Act: -0.1700

Data Index: 350849 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.4238. Min Act: -0.1700

Data Index: 1146679 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.3611. Min Act: -0.1700

Data Index: 372711 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.3611. Min Act: -0.1700

Data Index: 1358868 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.3768. Min Act: -0.1700

Data Index: 546799 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.3297. Min Act: -0.1700

Data Index: 295104 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.3454. Min Act: -0.1700

Data Index: 234474 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.2668. Min Act: -0.1700

Data Index: 14010 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.2983. Min Act: -0.1700

Data Index: 167642 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.3454. Min Act: -0.1700

Data Index: 397686 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.3611. Min Act: -0.1700

Data Index: 919108 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.2826. Min Act: -0.1700

Data Index: 1045160 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.2668. Min Act: -0.1700

Data Index: 679864 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.2826. Min Act: -0.1700

Data Index: 616176 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.2511. Min Act: -0.1700

Data Index: 892899 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.2354. Min Act: -0.1700

Data Index: 140435 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.2197. Min Act: -0.1700

Data Index: 1308602 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.2668. Min Act: -0.1700

Data Index: 137702 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.2354. Min Act: -0.1700

Data Index: 988543 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 3.4238. Min Range: -3.4238

Max Act: 3.2511. Min Act: -0.1700

Data Index: 962749 (C4 (Web Text))

Max Activating Token Index: 878