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

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

Neuron 536 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0232. Min Range: -5.0232

Max Act: 5.0232. Min Act: -0.1700

Data Index: 572649 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 5.0232. Min Range: -5.0232

Max Act: 5.0232. Min Act: -0.1700

Data Index: 905872 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 5.0232. Min Range: -5.0232

Max Act: 4.9919. Min Act: -0.1700

Data Index: 995167 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 5.0232. Min Range: -5.0232

Max Act: 4.9919. Min Act: -0.1700

Data Index: 1256587 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 5.0232. Min Range: -5.0232

Max Act: 4.9763. Min Act: -0.1700

Data Index: 1216182 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 5.0232. Min Range: -5.0232

Max Act: 5.0075. Min Act: -0.1700

Data Index: 1304717 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 5.0232. Min Range: -5.0232

Max Act: 5.0075. Min Act: -0.1700

Data Index: 507855 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 5.0232. Min Range: -5.0232

Max Act: 5.0075. Min Act: -0.1700

Data Index: 1065 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 5.0232. Min Range: -5.0232

Max Act: 4.9450. Min Act: -0.1700

Data Index: 548918 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 5.0232. Min Range: -5.0232

Max Act: 4.9450. Min Act: -0.1700

Data Index: 1026775 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 5.0232. Min Range: -5.0232

Max Act: 4.9450. Min Act: -0.1700

Data Index: 810173 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 5.0232. Min Range: -5.0232

Max Act: 4.8825. Min Act: -0.1700

Data Index: 586580 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 5.0232. Min Range: -5.0232

Max Act: 4.8982. Min Act: -0.1700

Data Index: 780963 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 5.0232. Min Range: -5.0232

Max Act: 4.9607. Min Act: -0.1700

Data Index: 652947 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 5.0232. Min Range: -5.0232

Max Act: 4.9138. Min Act: -0.1700

Data Index: 420083 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 5.0232. Min Range: -5.0232

Max Act: 4.8982. Min Act: -0.1700

Data Index: 235330 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 5.0232. Min Range: -5.0232

Max Act: 4.9607. Min Act: -0.1700

Data Index: 1304032 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 5.0232. Min Range: -5.0232

Max Act: 4.8669. Min Act: -0.1700

Data Index: 315481 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 5.0232. Min Range: -5.0232

Max Act: 4.9138. Min Act: -0.1700

Data Index: 627629 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 5.0232. Min Range: -5.0232

Max Act: 4.9138. Min Act: -0.1700

Data Index: 1276033 (C4 (Web Text))

Max Activating Token Index: 907