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

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

Neuron 1816 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: 7.7120. Min Range: -7.7120

Max Act: 7.7120. Min Act: -0.1700

Data Index: 763215 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 7.7120. Min Range: -7.7120

Max Act: 7.4932. Min Act: -0.1700

Data Index: 476770 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 7.7120. Min Range: -7.7120

Max Act: 7.3682. Min Act: -0.1700

Data Index: 330252 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 7.7120. Min Range: -7.7120

Max Act: 7.3995. Min Act: -0.1700

Data Index: 576838 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 7.7120. Min Range: -7.7120

Max Act: 7.3057. Min Act: -0.1700

Data Index: 83442 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 7.7120. Min Range: -7.7120

Max Act: 7.3370. Min Act: -0.1700

Data Index: 706306 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 7.7120. Min Range: -7.7120

Max Act: 7.2745. Min Act: -0.1700

Data Index: 1314737 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 7.7120. Min Range: -7.7120

Max Act: 7.2120. Min Act: -0.1700

Data Index: 1039755 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 7.7120. Min Range: -7.7120

Max Act: 7.2120. Min Act: -0.1700

Data Index: 500918 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 7.7120. Min Range: -7.7120

Max Act: 7.2120. Min Act: -0.1700

Data Index: 640741 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 7.7120. Min Range: -7.7120

Max Act: 7.1807. Min Act: -0.1700

Data Index: 256087 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 7.7120. Min Range: -7.7120

Max Act: 7.1495. Min Act: -0.1700

Data Index: 1061328 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 7.7120. Min Range: -7.7120

Max Act: 7.0557. Min Act: -0.1700

Data Index: 212175 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 7.7120. Min Range: -7.7120

Max Act: 7.1495. Min Act: -0.1700

Data Index: 1094129 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 7.7120. Min Range: -7.7120

Max Act: 7.0557. Min Act: -0.1700

Data Index: 54873 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 7.7120. Min Range: -7.7120

Max Act: 7.0557. Min Act: -0.1700

Data Index: 810544 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 7.7120. Min Range: -7.7120

Max Act: 6.9932. Min Act: -0.1700

Data Index: 481982 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 7.7120. Min Range: -7.7120

Max Act: 7.0557. Min Act: -0.1700

Data Index: 193885 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 7.7120. Min Range: -7.7120

Max Act: 6.9932. Min Act: -0.1700

Data Index: 879872 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 7.7120. Min Range: -7.7120

Max Act: 7.0245. Min Act: -0.1700

Data Index: 64527 (C4 (Web Text))

Max Activating Token Index: 809