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

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

Neuron 1315 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: 5.4211. Min Range: -5.4211

Max Act: 5.4211. Min Act: -0.1700

Data Index: 723073 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.3586. Min Act: -0.1700

Data Index: 604803 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.3273. Min Act: -0.1700

Data Index: 769817 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.3898. Min Act: -0.1700

Data Index: 849540 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.3586. Min Act: -0.1700

Data Index: 504306 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.3273. Min Act: -0.1700

Data Index: 880843 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.3586. Min Act: -0.1700

Data Index: 663277 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.2023. Min Act: -0.1700

Data Index: 723479 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.2023. Min Act: -0.1700

Data Index: 522481 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.2336. Min Act: -0.1700

Data Index: 2018 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.2023. Min Act: -0.1700

Data Index: 992364 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.1398. Min Act: -0.1700

Data Index: 751870 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.1086. Min Act: -0.1700

Data Index: 922554 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.1711. Min Act: -0.1700

Data Index: 326105 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.1711. Min Act: -0.1700

Data Index: 1236259 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.1398. Min Act: -0.1700

Data Index: 943237 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.1398. Min Act: -0.1700

Data Index: 173743 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.1398. Min Act: -0.1700

Data Index: 678450 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.0148. Min Act: -0.1700

Data Index: 767501 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 5.4211. Min Range: -5.4211

Max Act: 5.1398. Min Act: -0.1700

Data Index: 988463 (C4 (Web Text))

Max Activating Token Index: 49