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

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

Neuron 375 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: 3.5704. Min Range: -3.5704

Max Act: 3.5704. Min Act: -0.1700

Data Index: 586258 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.4764. Min Act: -0.1699

Data Index: 1156031 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.4764. Min Act: -0.1700

Data Index: 777255 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.4137. Min Act: -0.1700

Data Index: 778881 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.4137. Min Act: -0.1700

Data Index: 185405 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.4137. Min Act: -0.1700

Data Index: 1088905 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.3823. Min Act: -0.1700

Data Index: 367982 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.3510. Min Act: -0.1700

Data Index: 661760 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.3510. Min Act: -0.1700

Data Index: 948287 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.3510. Min Act: -0.1700

Data Index: 806302 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.2881. Min Act: -0.1700

Data Index: 533287 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.2567. Min Act: -0.1700

Data Index: 1378059 (Python Code)

Max Activating Token Index: 637

Text #12

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.2881. Min Act: -0.1700

Data Index: 217097 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.2881. Min Act: -0.1700

Data Index: 822218 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.2253. Min Act: -0.1699

Data Index: 817504 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.2881. Min Act: -0.1700

Data Index: 675551 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.2253. Min Act: -0.1700

Data Index: 1264175 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.2567. Min Act: -0.1700

Data Index: 413267 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.1938. Min Act: -0.1700

Data Index: 1033631 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 3.5704. Min Range: -3.5704

Max Act: 3.1938. Min Act: -0.1700

Data Index: 711310 (C4 (Web Text))

Max Activating Token Index: 199