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

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

Neuron 422 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 8.2701. Min Range: -8.2701

Max Act: 8.2701. Min Act: -0.1700

Data Index: 497650 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 8.2701. Min Range: -8.2701

Max Act: 8.0514. Min Act: -0.1700

Data Index: 155263 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.9576. Min Act: -0.1700

Data Index: 110421 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.8951. Min Act: -0.1700

Data Index: 1170624 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.9264. Min Act: -0.1700

Data Index: 1085299 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.9264. Min Act: -0.1700

Data Index: 528078 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.8014. Min Act: -0.1700

Data Index: 846158 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.7076. Min Act: -0.1700

Data Index: 1260709 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.7701. Min Act: -0.1700

Data Index: 1501 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.7076. Min Act: -0.1700

Data Index: 96259 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.8326. Min Act: -0.1700

Data Index: 354026 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.7701. Min Act: -0.1700

Data Index: 2457 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.7076. Min Act: -0.1700

Data Index: 161265 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.7389. Min Act: -0.1700

Data Index: 1289603 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.6764. Min Act: -0.1700

Data Index: 223503 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.6451. Min Act: -0.1700

Data Index: 118781 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.7076. Min Act: -0.1700

Data Index: 662437 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.7076. Min Act: -0.1700

Data Index: 824186 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.6451. Min Act: -0.1700

Data Index: 200580 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 8.2701. Min Range: -8.2701

Max Act: 7.6139. Min Act: -0.1700

Data Index: 644986 (C4 (Web Text))

Max Activating Token Index: 645