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

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

Neuron 1869 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1650. Min Range: -3.1650

Max Act: 3.1650. Min Act: -0.1700

Data Index: 1319970 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 3.1650. Min Range: -3.1650

Max Act: 3.1020. Min Act: -0.1700

Data Index: 522719 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 3.1650. Min Range: -3.1650

Max Act: 3.0389. Min Act: -0.1700

Data Index: 687918 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 3.1650. Min Range: -3.1650

Max Act: 3.0231. Min Act: -0.1700

Data Index: 512153 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 3.1650. Min Range: -3.1650

Max Act: 3.0073. Min Act: -0.1700

Data Index: 587471 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.9915. Min Act: -0.1700

Data Index: 1076861 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 3.1650. Min Range: -3.1650

Max Act: 3.0231. Min Act: -0.1700

Data Index: 28755 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.9915. Min Act: -0.1700

Data Index: 275326 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.9915. Min Act: -0.1700

Data Index: 954454 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.9915. Min Act: -0.1700

Data Index: 1113054 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.9757. Min Act: -0.1700

Data Index: 245213 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.9757. Min Act: -0.1700

Data Index: 797938 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.9757. Min Act: -0.1700

Data Index: 216069 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.9598. Min Act: -0.1700

Data Index: 896338 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.9757. Min Act: -0.1700

Data Index: 1064076 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.9757. Min Act: -0.1700

Data Index: 857025 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.9598. Min Act: -0.1700

Data Index: 30390 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.9440. Min Act: -0.1700

Data Index: 487812 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.9598. Min Act: -0.1700

Data Index: 98168 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 3.1650. Min Range: -3.1650

Max Act: 2.9598. Min Act: -0.1700

Data Index: 1288783 (C4 (Web Text))

Max Activating Token Index: 728