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

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

Neuron 1738 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.9195. Min Act: -0.1700

Data Index: 48362 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.7475. Min Act: -0.1700

Data Index: 767492 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.7788. Min Act: -0.1700

Data Index: 121146 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.7475. Min Act: -0.1700

Data Index: 693348 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6849. Min Act: -0.1700

Data Index: 1124783 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.7006. Min Act: -0.1700

Data Index: 536500 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6849. Min Act: -0.1700

Data Index: 379847 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.7006. Min Act: -0.1700

Data Index: 949751 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.7162. Min Act: -0.1700

Data Index: 596531 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6380. Min Act: -0.1700

Data Index: 797084 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6536. Min Act: -0.1700

Data Index: 295930 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6536. Min Act: -0.1700

Data Index: 1155509 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6693. Min Act: -0.1700

Data Index: 539607 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6380. Min Act: -0.1700

Data Index: 1192726 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6380. Min Act: -0.1700

Data Index: 1036835 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6066. Min Act: -0.1700

Data Index: 893390 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.5127. Min Act: -0.1700

Data Index: 754221 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6223. Min Act: -0.1700

Data Index: 547704 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6380. Min Act: -0.1700

Data Index: 1014495 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 3.9195. Min Range: -3.9195

Max Act: 3.6380. Min Act: -0.1700

Data Index: 328929 (C4 (Web Text))

Max Activating Token Index: 437