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

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

Neuron 513 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: 3.8018. Min Range: -3.8018

Max Act: 3.8018. Min Act: -0.1700

Data Index: 354108 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.7080. Min Act: -0.1700

Data Index: 664671 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.7080. Min Act: -0.1700

Data Index: 148688 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.6141. Min Act: -0.1700

Data Index: 1160958 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.7080. Min Act: -0.1700

Data Index: 575768 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.7080. Min Act: -0.1700

Data Index: 144424 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.6141. Min Act: -0.1700

Data Index: 432265 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.6454. Min Act: -0.1700

Data Index: 103488 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.6767. Min Act: -0.1700

Data Index: 2080 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.5827. Min Act: -0.1700

Data Index: 1274812 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.5514. Min Act: -0.1700

Data Index: 505528 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.7080. Min Act: -0.1700

Data Index: 8994 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.5514. Min Act: -0.1700

Data Index: 407454 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.5514. Min Act: -0.1700

Data Index: 846284 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.6767. Min Act: -0.1700

Data Index: 86259 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.5514. Min Act: -0.1700

Data Index: 316760 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.5201. Min Act: -0.1700

Data Index: 99643 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.5827. Min Act: -0.1700

Data Index: 439551 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.5827. Min Act: -0.1700

Data Index: 121511 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 3.8018. Min Range: -3.8018

Max Act: 3.5514. Min Act: -0.1700

Data Index: 1061467 (C4 (Web Text))

Max Activating Token Index: 66