Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 197 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.8107. Min Act: -0.1700

Data Index: 161341 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7012. Min Act: -0.1700

Data Index: 275431 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.6856. Min Act: -0.1700

Data Index: 413407 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.6856. Min Act: -0.1700

Data Index: 1058888 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.7012. Min Act: -0.1700

Data Index: 476576 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.6856. Min Act: -0.1700

Data Index: 568112 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.6699. Min Act: -0.1700

Data Index: 1375817 (Python Code)

Max Activating Token Index: 540

Text #7

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.6699. Min Act: -0.1700

Data Index: 1211997 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.6699. Min Act: -0.1700

Data Index: 1048147 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.6856. Min Act: -0.1700

Data Index: 424867 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.6856. Min Act: -0.1700

Data Index: 991042 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.6230. Min Act: -0.1700

Data Index: 1046422 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.6699. Min Act: -0.1700

Data Index: 86729 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.6230. Min Act: -0.1700

Data Index: 429068 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.6230. Min Act: -0.1700

Data Index: 472125 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.6073. Min Act: -0.1700

Data Index: 1332075 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.6230. Min Act: -0.1700

Data Index: 856523 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.6073. Min Act: -0.1700

Data Index: 501130 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.5604. Min Act: -0.1700

Data Index: 1144316 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 3.8107. Min Range: -3.8107

Max Act: 3.6073. Min Act: -0.1700

Data Index: 72746 (C4 (Web Text))

Max Activating Token Index: 431