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

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

Neuron 564 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.3758. Min Act: -0.1700

Data Index: 609645 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.3287. Min Act: -0.1700

Data Index: 969778 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2973. Min Act: -0.1700

Data Index: 580221 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.3130. Min Act: -0.1700

Data Index: 915083 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2973. Min Act: -0.1700

Data Index: 895893 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2659. Min Act: -0.1700

Data Index: 1075343 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2187. Min Act: -0.1700

Data Index: 228431 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2659. Min Act: -0.1700

Data Index: 28895 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2344. Min Act: -0.1700

Data Index: 410682 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2030. Min Act: -0.1700

Data Index: 1304038 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2030. Min Act: -0.1700

Data Index: 782655 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2187. Min Act: -0.1700

Data Index: 667799 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2030. Min Act: -0.1700

Data Index: 1264960 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2030. Min Act: -0.1700

Data Index: 687524 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2030. Min Act: -0.1700

Data Index: 881187 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1872. Min Act: -0.1700

Data Index: 66410 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1872. Min Act: -0.1700

Data Index: 207559 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.2030. Min Act: -0.1700

Data Index: 564101 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1715. Min Act: -0.1700

Data Index: 1305267 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 3.3758. Min Range: -3.3758

Max Act: 3.1400. Min Act: -0.1700

Data Index: 821381 (C4 (Web Text))

Max Activating Token Index: 587