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

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

Neuron 779 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: 3.2268. Min Range: -3.2268

Max Act: 3.2259. Min Act: -0.1700

Data Index: 883577 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 3.2268. Min Range: -3.2268

Max Act: 3.2268. Min Act: -0.1700

Data Index: 34796 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 3.2268. Min Range: -3.2268

Max Act: 3.1580. Min Act: -0.1700

Data Index: 134925 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 3.2268. Min Range: -3.2268

Max Act: 3.1213. Min Act: -0.1684

Data Index: 1265285 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 3.2268. Min Range: -3.2268

Max Act: 3.1251. Min Act: -0.1700

Data Index: 973010 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 3.2268. Min Range: -3.2268

Max Act: 3.0947. Min Act: -0.1700

Data Index: 78945 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 3.2268. Min Range: -3.2268

Max Act: 3.0705. Min Act: -0.1700

Data Index: 779061 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 3.2268. Min Range: -3.2268

Max Act: 3.0478. Min Act: -0.1699

Data Index: 1174507 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 3.2268. Min Range: -3.2268

Max Act: 3.0363. Min Act: -0.1690

Data Index: 667664 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 3.2268. Min Range: -3.2268

Max Act: 3.0307. Min Act: -0.1700

Data Index: 14664 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 3.2268. Min Range: -3.2268

Max Act: 3.0279. Min Act: -0.1084

Data Index: 1039753 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 3.2268. Min Range: -3.2268

Max Act: 3.0262. Min Act: -0.1677

Data Index: 483463 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 3.2268. Min Range: -3.2268

Max Act: 3.0290. Min Act: -0.1700

Data Index: 411770 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 3.2268. Min Range: -3.2268

Max Act: 2.9889. Min Act: -0.1700

Data Index: 1292511 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 3.2268. Min Range: -3.2268

Max Act: 3.0149. Min Act: -0.1693

Data Index: 714945 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 3.2268. Min Range: -3.2268

Max Act: 2.9947. Min Act: -0.1699

Data Index: 896915 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 3.2268. Min Range: -3.2268

Max Act: 2.9886. Min Act: -0.1700

Data Index: 544388 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 3.2268. Min Range: -3.2268

Max Act: 3.0063. Min Act: -0.1700

Data Index: 45401 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 3.2268. Min Range: -3.2268

Max Act: 2.9824. Min Act: -0.1700

Data Index: 1635547 (Python Code)

Max Activating Token Index: 591

Text #19

Max Range: 3.2268. Min Range: -3.2268

Max Act: 2.9755. Min Act: -0.1700

Data Index: 825886 (C4 (Web Text))

Max Activating Token Index: 65