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

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

Neuron 1979 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: 3.8028. Min Range: -3.8028

Max Act: 3.7403. Min Act: -0.1700

Data Index: 637857 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.8028. Min Act: -0.1700

Data Index: 716176 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.7403. Min Act: -0.1700

Data Index: 1212083 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.7090. Min Act: -0.1700

Data Index: 48556 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.7090. Min Act: -0.1700

Data Index: 505294 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.7090. Min Act: -0.1700

Data Index: 1164394 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.6777. Min Act: -0.1700

Data Index: 50039 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.6464. Min Act: -0.1700

Data Index: 1210853 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.6777. Min Act: -0.1700

Data Index: 569327 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.6777. Min Act: -0.1700

Data Index: 431660 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.6777. Min Act: -0.1700

Data Index: 825062 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.6464. Min Act: -0.1700

Data Index: 751667 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.6777. Min Act: -0.1700

Data Index: 1014171 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.6151. Min Act: -0.1700

Data Index: 755598 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.6464. Min Act: -0.1700

Data Index: 986041 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.6464. Min Act: -0.1700

Data Index: 43030 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.6464. Min Act: -0.1700

Data Index: 309247 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.5838. Min Act: -0.1700

Data Index: 259080 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.5838. Min Act: -0.1700

Data Index: 714061 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 3.8028. Min Range: -3.8028

Max Act: 3.5838. Min Act: -0.1700

Data Index: 654474 (C4 (Web Text))

Max Activating Token Index: 61