Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1028 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.8870. Min Act: -0.1700

Data Index: 100899 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.8714. Min Act: -0.1700

Data Index: 914349 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7932. Min Act: -0.1700

Data Index: 1226783 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7932. Min Act: -0.1700

Data Index: 374463 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7932. Min Act: -0.1700

Data Index: 152 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7932. Min Act: -0.1700

Data Index: 128455 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7932. Min Act: -0.1700

Data Index: 721291 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7932. Min Act: -0.1700

Data Index: 1125580 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7776. Min Act: -0.1700

Data Index: 1292552 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7619. Min Act: -0.1700

Data Index: 1058522 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7619. Min Act: -0.1700

Data Index: 445516 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7463. Min Act: -0.1700

Data Index: 569504 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7463. Min Act: -0.1700

Data Index: 729568 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7619. Min Act: -0.1700

Data Index: 179037 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7619. Min Act: -0.1700

Data Index: 164618 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7619. Min Act: -0.1700

Data Index: 1044787 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7619. Min Act: -0.1700

Data Index: 531480 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7463. Min Act: -0.1700

Data Index: 721336 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7463. Min Act: -0.1700

Data Index: 752641 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.7463. Min Act: -0.1700

Data Index: 426487 (C4 (Web Text))

Max Activating Token Index: 617