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

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

Neuron 1553 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: 5.0545. Min Range: -5.0545

Max Act: 5.0545. Min Act: -0.1700

Data Index: 921120 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 5.0545. Min Range: -5.0545

Max Act: 5.0545. Min Act: -0.1700

Data Index: 1272502 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 5.0545. Min Range: -5.0545

Max Act: 5.0232. Min Act: -0.1700

Data Index: 79447 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 5.0545. Min Range: -5.0545

Max Act: 5.0232. Min Act: -0.1700

Data Index: 1144195 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 5.0545. Min Range: -5.0545

Max Act: 4.9920. Min Act: -0.1700

Data Index: 362878 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 5.0545. Min Range: -5.0545

Max Act: 4.8982. Min Act: -0.1700

Data Index: 144356 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 5.0545. Min Range: -5.0545

Max Act: 4.9295. Min Act: -0.1700

Data Index: 820379 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 5.0545. Min Range: -5.0545

Max Act: 4.8670. Min Act: -0.1700

Data Index: 757524 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 5.0545. Min Range: -5.0545

Max Act: 4.8670. Min Act: -0.1700

Data Index: 1248070 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 5.0545. Min Range: -5.0545

Max Act: 4.8357. Min Act: -0.1700

Data Index: 768326 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 5.0545. Min Range: -5.0545

Max Act: 4.8357. Min Act: -0.1700

Data Index: 826866 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 5.0545. Min Range: -5.0545

Max Act: 4.8045. Min Act: -0.1700

Data Index: 874073 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 5.0545. Min Range: -5.0545

Max Act: 4.7420. Min Act: -0.1700

Data Index: 919441 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 5.0545. Min Range: -5.0545

Max Act: 4.7420. Min Act: -0.1700

Data Index: 321520 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 5.0545. Min Range: -5.0545

Max Act: 4.7420. Min Act: -0.1700

Data Index: 1039139 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 5.0545. Min Range: -5.0545

Max Act: 4.7420. Min Act: -0.1700

Data Index: 308866 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 5.0545. Min Range: -5.0545

Max Act: 4.7107. Min Act: -0.1700

Data Index: 460744 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 5.0545. Min Range: -5.0545

Max Act: 4.7420. Min Act: -0.1700

Data Index: 289733 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 5.0545. Min Range: -5.0545

Max Act: 4.8045. Min Act: -0.1700

Data Index: 1034512 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 5.0545. Min Range: -5.0545

Max Act: 4.7732. Min Act: -0.1700

Data Index: 922723 (C4 (Web Text))

Max Activating Token Index: 463