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

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

Neuron 523 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: 5.2940. Min Range: -5.2940

Max Act: 5.2940. Min Act: -0.1700

Data Index: 907300 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.2003. Min Act: -0.1700

Data Index: 104666 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.1534. Min Act: -0.1700

Data Index: 301272 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.1534. Min Act: -0.1700

Data Index: 1346945 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0909. Min Act: -0.1700

Data Index: 1008433 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0596. Min Act: -0.1700

Data Index: 816551 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0596. Min Act: -0.1700

Data Index: 177667 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.1065. Min Act: -0.1700

Data Index: 922601 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0753. Min Act: -0.1700

Data Index: 566048 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 5.2940. Min Range: -5.2940

Max Act: 4.9971. Min Act: -0.1700

Data Index: 539141 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0753. Min Act: -0.1700

Data Index: 1048198 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 5.2940. Min Range: -5.2940

Max Act: 4.9815. Min Act: -0.1700

Data Index: 814092 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 5.2940. Min Range: -5.2940

Max Act: 4.9971. Min Act: -0.1700

Data Index: 801037 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 5.2940. Min Range: -5.2940

Max Act: 4.9815. Min Act: -0.1700

Data Index: 1076064 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 5.2940. Min Range: -5.2940

Max Act: 4.9346. Min Act: -0.1700

Data Index: 1232818 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 5.2940. Min Range: -5.2940

Max Act: 4.9971. Min Act: -0.1700

Data Index: 156938 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 5.2940. Min Range: -5.2940

Max Act: 4.9659. Min Act: -0.1700

Data Index: 998282 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 5.2940. Min Range: -5.2940

Max Act: 4.9503. Min Act: -0.1700

Data Index: 1132820 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 5.2940. Min Range: -5.2940

Max Act: 4.9659. Min Act: -0.1700

Data Index: 1249773 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 5.2940. Min Range: -5.2940

Max Act: 4.9659. Min Act: -0.1700

Data Index: 1036435 (C4 (Web Text))

Max Activating Token Index: 590