Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 25 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.8090. Min Act: -0.1700

Data Index: 1177277 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.7464. Min Act: -0.1700

Data Index: 840895 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.7777. Min Act: -0.1700

Data Index: 930934 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.7464. Min Act: -0.1700

Data Index: 379781 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.7464. Min Act: -0.1700

Data Index: 818970 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.7151. Min Act: -0.1700

Data Index: 1332714 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.7151. Min Act: -0.1700

Data Index: 858203 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.6838. Min Act: -0.1700

Data Index: 703479 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.6525. Min Act: -0.1700

Data Index: 1285229 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.6525. Min Act: -0.1700

Data Index: 955491 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.6525. Min Act: -0.1700

Data Index: 755600 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.6212. Min Act: -0.1700

Data Index: 675905 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.6525. Min Act: -0.1700

Data Index: 972961 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.6212. Min Act: -0.1700

Data Index: 13357 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.6212. Min Act: -0.1700

Data Index: 247937 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.6212. Min Act: -0.1700

Data Index: 77912 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.5899. Min Act: -0.1700

Data Index: 310802 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.5899. Min Act: -0.1700

Data Index: 597937 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.5586. Min Act: -0.1700

Data Index: 91176 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 3.8090. Min Range: -3.8090

Max Act: 3.6212. Min Act: -0.1700

Data Index: 628701 (C4 (Web Text))

Max Activating Token Index: 281