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

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

Neuron 501 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: 3.5499. Min Range: -3.5499

Max Act: 3.5499. Min Act: -0.1700

Data Index: 154033 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.5185. Min Act: -0.1700

Data Index: 1161231 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.4558. Min Act: -0.1700

Data Index: 197490 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.3931. Min Act: -0.1699

Data Index: 286818 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.3304. Min Act: -0.1700

Data Index: 1612853 (Python Code)

Max Activating Token Index: 675

Text #5

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.2989. Min Act: -0.1700

Data Index: 1546980 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.3617. Min Act: -0.1700

Data Index: 1557950 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.3304. Min Act: -0.1700

Data Index: 1389118 (Python Code)

Max Activating Token Index: 743

Text #8

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.3304. Min Act: -0.1700

Data Index: 1237026 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.3617. Min Act: -0.1700

Data Index: 71463 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.2989. Min Act: -0.1700

Data Index: 945341 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.3304. Min Act: -0.1700

Data Index: 1336786 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.2989. Min Act: -0.1700

Data Index: 935825 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.2675. Min Act: -0.1700

Data Index: 296270 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.2675. Min Act: -0.1700

Data Index: 736829 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.2675. Min Act: -0.1700

Data Index: 537447 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.2046. Min Act: -0.1700

Data Index: 955145 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.2675. Min Act: -0.1700

Data Index: 1537199 (Python Code)

Max Activating Token Index: 43

Text #18

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.2675. Min Act: -0.1700

Data Index: 112382 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 3.5499. Min Range: -3.5499

Max Act: 3.2046. Min Act: -0.1700

Data Index: 494451 (C4 (Web Text))

Max Activating Token Index: 384