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

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

Neuron 779 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.7919. Min Act: -0.1700

Data Index: 1252196 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.8232. Min Act: -0.1700

Data Index: 676426 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.7919. Min Act: -0.1700

Data Index: 1217713 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.7606. Min Act: -0.1700

Data Index: 804201 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.7293. Min Act: -0.1700

Data Index: 1101549 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.6980. Min Act: -0.1700

Data Index: 1144074 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.6980. Min Act: -0.1700

Data Index: 752812 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.6667. Min Act: -0.1700

Data Index: 787712 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.7293. Min Act: -0.1700

Data Index: 672285 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.6354. Min Act: -0.1700

Data Index: 304579 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.6667. Min Act: -0.1700

Data Index: 209277 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.6354. Min Act: -0.1700

Data Index: 711853 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.6354. Min Act: -0.1700

Data Index: 470182 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.6667. Min Act: -0.1700

Data Index: 321639 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.6354. Min Act: -0.1700

Data Index: 107951 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.6354. Min Act: -0.1700

Data Index: 873617 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.6354. Min Act: -0.1700

Data Index: 181395 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.6354. Min Act: -0.1700

Data Index: 739268 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.6041. Min Act: -0.1700

Data Index: 514869 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 3.8232. Min Range: -3.8232

Max Act: 3.5728. Min Act: -0.1700

Data Index: 290256 (C4 (Web Text))

Max Activating Token Index: 1004