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

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

Neuron 1337 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: 8.0725. Min Range: -8.0725

Max Act: 8.0725. Min Act: -0.1700

Data Index: 428103 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.8225. Min Act: -0.1700

Data Index: 512045 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.6975. Min Act: -0.1700

Data Index: 841073 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.5725. Min Act: -0.1700

Data Index: 47273 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.6350. Min Act: -0.1700

Data Index: 803255 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.5100. Min Act: -0.1700

Data Index: 574781 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.5100. Min Act: -0.1699

Data Index: 62784 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.4475. Min Act: -0.1700

Data Index: 73264 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.3850. Min Act: -0.1700

Data Index: 257085 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.4475. Min Act: -0.1700

Data Index: 842796 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.3850. Min Act: -0.1700

Data Index: 396516 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.4475. Min Act: -0.1700

Data Index: 821946 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.3850. Min Act: -0.1700

Data Index: 755778 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.4475. Min Act: -0.1700

Data Index: 954090 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.3850. Min Act: -0.1700

Data Index: 58220 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.4475. Min Act: -0.1700

Data Index: 1163100 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.1975. Min Act: -0.1700

Data Index: 102597 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.2600. Min Act: -0.1700

Data Index: 775160 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.2600. Min Act: -0.1700

Data Index: 988241 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 8.0725. Min Range: -8.0725

Max Act: 7.2600. Min Act: -0.1700

Data Index: 138904 (C4 (Web Text))

Max Activating Token Index: 707