Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 101 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.5844. Min Act: -0.1700

Data Index: 350189 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.5704. Min Act: -0.1700

Data Index: 746230 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.4373. Min Act: -0.1700

Data Index: 1085031 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.4502. Min Act: -0.1700

Data Index: 179090 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.3974. Min Act: -0.1700

Data Index: 645177 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.3832. Min Act: -0.1700

Data Index: 361349 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.3625. Min Act: -0.1700

Data Index: 972148 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.3313. Min Act: -0.1700

Data Index: 732927 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.3150. Min Act: -0.1700

Data Index: 1271912 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.3344. Min Act: -0.1700

Data Index: 291981 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.3456. Min Act: -0.1700

Data Index: 86343 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.3045. Min Act: -0.1700

Data Index: 259732 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.3038. Min Act: -0.1700

Data Index: 1356650 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.3289. Min Act: -0.1700

Data Index: 1090431 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.3015. Min Act: -0.1700

Data Index: 621327 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.2768. Min Act: -0.1700

Data Index: 936809 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.2742. Min Act: -0.1700

Data Index: 628887 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.2806. Min Act: -0.1700

Data Index: 734044 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.2508. Min Act: -0.1700

Data Index: 718990 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 3.5844. Min Range: -3.5844

Max Act: 3.2693. Min Act: -0.1700

Data Index: 1020733 (C4 (Web Text))

Max Activating Token Index: 254