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

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

Neuron 243 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.6624. Min Act: -0.1700

Data Index: 228923 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.5999. Min Act: -0.1700

Data Index: 77757 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.5374. Min Act: -0.1700

Data Index: 1036268 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.5374. Min Act: -0.1700

Data Index: 739491 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.5062. Min Act: -0.1700

Data Index: 1040437 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.4749. Min Act: -0.1700

Data Index: 795100 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.4749. Min Act: -0.1700

Data Index: 836296 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.5062. Min Act: -0.1700

Data Index: 903991 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.4124. Min Act: -0.1700

Data Index: 147372 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.4124. Min Act: -0.1700

Data Index: 725990 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.3499. Min Act: -0.1700

Data Index: 498190 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.4124. Min Act: -0.1700

Data Index: 951767 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.3812. Min Act: -0.1700

Data Index: 96622 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.3187. Min Act: -0.1700

Data Index: 1268343 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.3499. Min Act: -0.1700

Data Index: 494235 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.3499. Min Act: -0.1700

Data Index: 1314874 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.3187. Min Act: -0.1700

Data Index: 511269 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.2562. Min Act: -0.1700

Data Index: 328629 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.2874. Min Act: -0.1700

Data Index: 546666 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 5.6624. Min Range: -5.6624

Max Act: 5.2874. Min Act: -0.1700

Data Index: 649195 (C4 (Web Text))

Max Activating Token Index: 577