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

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

Neuron 654 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5695. Min Act: -0.1700

Data Index: 422151 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5538. Min Act: -0.1700

Data Index: 499906 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5538. Min Act: -0.1700

Data Index: 368015 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5382. Min Act: -0.1700

Data Index: 431428 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5382. Min Act: -0.1700

Data Index: 338111 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5225. Min Act: -0.1700

Data Index: 1351290 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5068. Min Act: -0.1700

Data Index: 355270 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5225. Min Act: -0.1700

Data Index: 1298274 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4912. Min Act: -0.1700

Data Index: 860190 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4912. Min Act: -0.1700

Data Index: 1288758 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4755. Min Act: -0.1700

Data Index: 1163013 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4598. Min Act: -0.1700

Data Index: 731726 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4755. Min Act: -0.1700

Data Index: 1454 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4598. Min Act: -0.1700

Data Index: 85266 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4598. Min Act: -0.1700

Data Index: 671310 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4441. Min Act: -0.1700

Data Index: 1217057 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4285. Min Act: -0.1700

Data Index: 1042686 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4285. Min Act: -0.1700

Data Index: 501109 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4598. Min Act: -0.1700

Data Index: 755993 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.4441. Min Act: -0.1700

Data Index: 1212898 (C4 (Web Text))

Max Activating Token Index: 796