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

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

Neuron 718 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.7571. Min Act: -0.1700

Data Index: 91561 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.6611. Min Act: -0.1700

Data Index: 645133 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.6771. Min Act: -0.1700

Data Index: 805578 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.6611. Min Act: -0.1700

Data Index: 782060 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.6450. Min Act: -0.1700

Data Index: 1101797 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.6450. Min Act: -0.1700

Data Index: 1021552 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.6290. Min Act: -0.1700

Data Index: 1192442 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.6290. Min Act: -0.1700

Data Index: 661235 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.6290. Min Act: -0.1700

Data Index: 1249236 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.6129. Min Act: -0.1700

Data Index: 1330497 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.6129. Min Act: -0.1700

Data Index: 1203284 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.6129. Min Act: -0.1700

Data Index: 670664 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.6129. Min Act: -0.1700

Data Index: 112975 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.6129. Min Act: -0.1700

Data Index: 788082 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.6129. Min Act: -0.1700

Data Index: 486449 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.6129. Min Act: -0.1700

Data Index: 164347 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.5968. Min Act: -0.1700

Data Index: 291915 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.5968. Min Act: -0.1700

Data Index: 1181228 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.5968. Min Act: -0.1700

Data Index: 634602 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.5968. Min Act: -0.1700

Data Index: 406764 (C4 (Web Text))

Max Activating Token Index: 792