Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 930 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 4.0663. Min Range: -4.0663

Max Act: 4.0663. Min Act: -0.1700

Data Index: 650573 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 4.0663. Min Range: -4.0663

Max Act: 4.0038. Min Act: -0.1700

Data Index: 331466 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.9725. Min Act: -0.1700

Data Index: 387780 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.9412. Min Act: -0.1700

Data Index: 1167331 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.9100. Min Act: -0.1700

Data Index: 1250261 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8943. Min Act: -0.1700

Data Index: 265008 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8943. Min Act: -0.1700

Data Index: 68975 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8631. Min Act: -0.1700

Data Index: 1166362 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8787. Min Act: -0.1700

Data Index: 690545 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8787. Min Act: -0.1700

Data Index: 85132 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8474. Min Act: -0.1700

Data Index: 700305 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8631. Min Act: -0.1700

Data Index: 1182594 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8787. Min Act: -0.1700

Data Index: 35972 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8318. Min Act: -0.1700

Data Index: 246282 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8474. Min Act: -0.1700

Data Index: 507864 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8631. Min Act: -0.1700

Data Index: 1140206 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8161. Min Act: -0.1700

Data Index: 1046515 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8318. Min Act: -0.1700

Data Index: 1064585 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8474. Min Act: -0.1700

Data Index: 521229 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 4.0663. Min Range: -4.0663

Max Act: 3.8474. Min Act: -0.1700

Data Index: 400600 (C4 (Web Text))

Max Activating Token Index: 942