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

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

Neuron 192 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: 5.1315. Min Range: -5.1315

Max Act: 5.1002. Min Act: -0.1700

Data Index: 1010557 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 5.1315. Min Range: -5.1315

Max Act: 5.1315. Min Act: -0.1700

Data Index: 422114 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 5.1315. Min Range: -5.1315

Max Act: 5.0377. Min Act: -0.1700

Data Index: 516856 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 5.1315. Min Range: -5.1315

Max Act: 4.9752. Min Act: -0.1700

Data Index: 771490 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 5.1315. Min Range: -5.1315

Max Act: 4.9752. Min Act: -0.1700

Data Index: 1222554 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 5.1315. Min Range: -5.1315

Max Act: 4.9127. Min Act: -0.1700

Data Index: 1228952 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 5.1315. Min Range: -5.1315

Max Act: 4.8502. Min Act: -0.1700

Data Index: 662039 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 5.1315. Min Range: -5.1315

Max Act: 4.8815. Min Act: -0.1700

Data Index: 687077 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 5.1315. Min Range: -5.1315

Max Act: 4.8502. Min Act: -0.1700

Data Index: 996548 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 5.1315. Min Range: -5.1315

Max Act: 4.8190. Min Act: -0.1700

Data Index: 166920 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 5.1315. Min Range: -5.1315

Max Act: 4.9127. Min Act: -0.1700

Data Index: 211153 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 5.1315. Min Range: -5.1315

Max Act: 4.8190. Min Act: -0.1700

Data Index: 143784 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 5.1315. Min Range: -5.1315

Max Act: 4.8190. Min Act: -0.1700

Data Index: 1126881 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 5.1315. Min Range: -5.1315

Max Act: 4.8190. Min Act: -0.1700

Data Index: 1030048 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 5.1315. Min Range: -5.1315

Max Act: 4.8502. Min Act: -0.1700

Data Index: 214777 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 5.1315. Min Range: -5.1315

Max Act: 4.8190. Min Act: -0.1700

Data Index: 713124 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 5.1315. Min Range: -5.1315

Max Act: 4.8190. Min Act: -0.1700

Data Index: 140640 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 5.1315. Min Range: -5.1315

Max Act: 4.7565. Min Act: -0.1700

Data Index: 975369 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 5.1315. Min Range: -5.1315

Max Act: 4.7565. Min Act: -0.1700

Data Index: 652004 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 5.1315. Min Range: -5.1315

Max Act: 4.7877. Min Act: -0.1700

Data Index: 320341 (C4 (Web Text))

Max Activating Token Index: 699