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

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

Neuron 901 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: 5.5284. Min Range: -5.5284

Max Act: 5.5284. Min Act: -0.1700

Data Index: 934011 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 5.5284. Min Range: -5.5284

Max Act: 5.3722. Min Act: -0.1700

Data Index: 1196823 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 5.5284. Min Range: -5.5284

Max Act: 5.3409. Min Act: -0.1700

Data Index: 539149 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 5.5284. Min Range: -5.5284

Max Act: 5.3409. Min Act: -0.1700

Data Index: 249619 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 5.5284. Min Range: -5.5284

Max Act: 5.2159. Min Act: -0.1700

Data Index: 1018029 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 5.5284. Min Range: -5.5284

Max Act: 5.2159. Min Act: -0.1700

Data Index: 65236 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 5.5284. Min Range: -5.5284

Max Act: 5.0597. Min Act: -0.1700

Data Index: 181891 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 5.5284. Min Range: -5.5284

Max Act: 5.0909. Min Act: -0.1700

Data Index: 390081 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 5.5284. Min Range: -5.5284

Max Act: 5.0909. Min Act: -0.1700

Data Index: 197802 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 5.5284. Min Range: -5.5284

Max Act: 5.0284. Min Act: -0.1700

Data Index: 1277909 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 5.5284. Min Range: -5.5284

Max Act: 5.0597. Min Act: -0.1700

Data Index: 189185 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 5.5284. Min Range: -5.5284

Max Act: 5.0597. Min Act: -0.1700

Data Index: 872080 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 5.5284. Min Range: -5.5284

Max Act: 5.0284. Min Act: -0.1700

Data Index: 868393 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 5.5284. Min Range: -5.5284

Max Act: 5.0284. Min Act: -0.1700

Data Index: 633874 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 5.5284. Min Range: -5.5284

Max Act: 4.9972. Min Act: -0.1700

Data Index: 1046492 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 5.5284. Min Range: -5.5284

Max Act: 4.9972. Min Act: -0.1700

Data Index: 864253 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 5.5284. Min Range: -5.5284

Max Act: 4.9659. Min Act: -0.1700

Data Index: 46632 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 5.5284. Min Range: -5.5284

Max Act: 4.9972. Min Act: -0.1700

Data Index: 400103 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 5.5284. Min Range: -5.5284

Max Act: 4.9659. Min Act: -0.1700

Data Index: 394079 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 5.5284. Min Range: -5.5284

Max Act: 4.9972. Min Act: -0.1700

Data Index: 1165474 (C4 (Web Text))

Max Activating Token Index: 837