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

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

Neuron 1889 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.6719. Min Act: -0.1700

Data Index: 1232987 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.7031. Min Act: -0.1700

Data Index: 259080 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.6562. Min Act: -0.1700

Data Index: 1085301 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.6406. Min Act: -0.1700

Data Index: 1210853 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.6406. Min Act: -0.1700

Data Index: 1028015 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.6250. Min Act: -0.1700

Data Index: 1148896 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.5625. Min Act: -0.1700

Data Index: 505294 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.5469. Min Act: -0.1700

Data Index: 986041 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.5625. Min Act: -0.1700

Data Index: 1014171 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.5469. Min Act: -0.1700

Data Index: 550561 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.5469. Min Act: -0.1700

Data Index: 755598 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.5469. Min Act: -0.1700

Data Index: 1212083 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.6094. Min Act: -0.1700

Data Index: 431660 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.5156. Min Act: -0.1700

Data Index: 637857 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.5781. Min Act: -0.1700

Data Index: 527649 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.5312. Min Act: -0.1700

Data Index: 113865 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.5000. Min Act: -0.1700

Data Index: 1166460 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.4375. Min Act: -0.1700

Data Index: 1303056 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.4375. Min Act: -0.1700

Data Index: 252273 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 5.7031. Min Range: -5.7031

Max Act: 5.4844. Min Act: -0.1700

Data Index: 43030 (C4 (Web Text))

Max Activating Token Index: 161