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

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

Neuron 1019 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: 3.7832. Min Range: -3.7832

Max Act: 3.7832. Min Act: -0.1700

Data Index: 601931 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.7832. Min Act: -0.1700

Data Index: 1000994 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.7519. Min Act: -0.1700

Data Index: 1083167 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.7519. Min Act: -0.1700

Data Index: 857219 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.7519. Min Act: -0.1700

Data Index: 196494 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.7206. Min Act: -0.1700

Data Index: 33069 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.6893. Min Act: -0.1700

Data Index: 886631 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.6580. Min Act: -0.1700

Data Index: 521606 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.6893. Min Act: -0.1700

Data Index: 454002 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.6893. Min Act: -0.1700

Data Index: 1301723 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.6893. Min Act: -0.1700

Data Index: 499917 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.6580. Min Act: -0.1700

Data Index: 899048 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.6580. Min Act: -0.1700

Data Index: 937904 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.6267. Min Act: -0.1700

Data Index: 306338 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.6893. Min Act: -0.1700

Data Index: 75943 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.6267. Min Act: -0.1700

Data Index: 527850 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.6580. Min Act: -0.1700

Data Index: 842483 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.6580. Min Act: -0.1700

Data Index: 593116 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.5954. Min Act: -0.1700

Data Index: 702147 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 3.7832. Min Range: -3.7832

Max Act: 3.6267. Min Act: -0.1700

Data Index: 213411 (C4 (Web Text))

Max Activating Token Index: 133