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

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

Neuron 1476 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.8642. Min Act: -0.1700

Data Index: 1294763 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 7.0517. Min Range: -7.0517

Max Act: 7.0205. Min Act: -0.1700

Data Index: 1283610 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 7.0517. Min Range: -7.0517

Max Act: 7.0517. Min Act: -0.1700

Data Index: 302963 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.9580. Min Act: -0.1700

Data Index: 647353 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.9892. Min Act: -0.1700

Data Index: 30262 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.9892. Min Act: -0.1700

Data Index: 181023 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.9580. Min Act: -0.1700

Data Index: 241300 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.8017. Min Act: -0.1700

Data Index: 1148160 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.8017. Min Act: -0.1700

Data Index: 972819 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.8330. Min Act: -0.1700

Data Index: 639747 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.7705. Min Act: -0.1700

Data Index: 316192 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.7080. Min Act: -0.1700

Data Index: 916447 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.7705. Min Act: -0.1700

Data Index: 1313748 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.7392. Min Act: -0.1700

Data Index: 1229141 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.7392. Min Act: -0.1700

Data Index: 1213087 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.7080. Min Act: -0.1700

Data Index: 212626 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.7705. Min Act: -0.1700

Data Index: 77073 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.7392. Min Act: -0.1700

Data Index: 931412 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.6767. Min Act: -0.1700

Data Index: 906247 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 7.0517. Min Range: -7.0517

Max Act: 6.6455. Min Act: -0.1700

Data Index: 137905 (C4 (Web Text))

Max Activating Token Index: 232