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

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

Neuron 1892 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: 5.1267. Min Range: -5.1267

Max Act: 5.1267. Min Act: -0.1700

Data Index: 345085 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.8767. Min Act: -0.1700

Data Index: 58208 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.7829. Min Act: -0.1700

Data Index: 399127 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.7829. Min Act: -0.1700

Data Index: 1348890 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.6892. Min Act: -0.1700

Data Index: 97580 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.6892. Min Act: -0.1700

Data Index: 985848 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.6579. Min Act: -0.1700

Data Index: 415634 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.6267. Min Act: -0.1700

Data Index: 852983 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.6579. Min Act: -0.1700

Data Index: 198051 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.6579. Min Act: -0.1700

Data Index: 1350983 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.6579. Min Act: -0.1700

Data Index: 924653 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.6892. Min Act: -0.1700

Data Index: 936984 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.6267. Min Act: -0.1700

Data Index: 1108324 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.6267. Min Act: -0.1700

Data Index: 724558 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.6267. Min Act: -0.1700

Data Index: 572600 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.5954. Min Act: -0.1700

Data Index: 350059 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.6267. Min Act: -0.1700

Data Index: 511427 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.6267. Min Act: -0.1700

Data Index: 1210213 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.5954. Min Act: -0.1700

Data Index: 269212 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 5.1267. Min Range: -5.1267

Max Act: 4.6267. Min Act: -0.1700

Data Index: 1009164 (C4 (Web Text))

Max Activating Token Index: 918