Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 359 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.1281. Min Range: -3.1281

Max Act: 3.1281. Min Act: -0.1700

Data Index: 1166507 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 3.1281. Min Range: -3.1281

Max Act: 3.0650. Min Act: -0.1700

Data Index: 225365 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 3.1281. Min Range: -3.1281

Max Act: 3.0492. Min Act: -0.1700

Data Index: 511752 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 3.1281. Min Range: -3.1281

Max Act: 2.9860. Min Act: -0.1700

Data Index: 503843 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 3.1281. Min Range: -3.1281

Max Act: 2.9544. Min Act: -0.1700

Data Index: 855203 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 3.1281. Min Range: -3.1281

Max Act: 2.9544. Min Act: -0.1434

Data Index: 726199 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 3.1281. Min Range: -3.1281

Max Act: 2.9068. Min Act: -0.1700

Data Index: 367450 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 3.1281. Min Range: -3.1281

Max Act: 2.9227. Min Act: -0.1700

Data Index: 979142 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 3.1281. Min Range: -3.1281

Max Act: 2.8751. Min Act: -0.1699

Data Index: 1062338 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 3.1281. Min Range: -3.1281

Max Act: 2.8592. Min Act: -0.1630

Data Index: 694066 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 3.1281. Min Range: -3.1281

Max Act: 2.8592. Min Act: -0.1700

Data Index: 531819 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 3.1281. Min Range: -3.1281

Max Act: 2.8433. Min Act: -0.1700

Data Index: 878792 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 3.1281. Min Range: -3.1281

Max Act: 2.8433. Min Act: -0.1700

Data Index: 94365 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 3.1281. Min Range: -3.1281

Max Act: 2.8592. Min Act: -0.1700

Data Index: 315868 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 3.1281. Min Range: -3.1281

Max Act: 2.8274. Min Act: -0.1700

Data Index: 998485 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 3.1281. Min Range: -3.1281

Max Act: 2.7956. Min Act: -0.1700

Data Index: 236948 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 3.1281. Min Range: -3.1281

Max Act: 2.7956. Min Act: -0.1700

Data Index: 1186690 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 3.1281. Min Range: -3.1281

Max Act: 2.7797. Min Act: -0.1700

Data Index: 786959 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 3.1281. Min Range: -3.1281

Max Act: 2.7797. Min Act: -0.1700

Data Index: 397647 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 3.1281. Min Range: -3.1281

Max Act: 2.7797. Min Act: -0.1700

Data Index: 612966 (C4 (Web Text))

Max Activating Token Index: 727