Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 396 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.1619. Min Range: -5.1619

Max Act: 5.1619. Min Act: -0.1700

Data Index: 1198145 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 5.1619. Min Range: -5.1619

Max Act: 5.1619. Min Act: -0.1700

Data Index: 919525 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 5.1619. Min Range: -5.1619

Max Act: 5.1307. Min Act: -0.1700

Data Index: 339746 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 5.1619. Min Range: -5.1619

Max Act: 5.1619. Min Act: -0.1700

Data Index: 266127 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 5.1619. Min Range: -5.1619

Max Act: 5.1619. Min Act: -0.1700

Data Index: 1280389 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 5.1619. Min Range: -5.1619

Max Act: 5.0994. Min Act: -0.1700

Data Index: 704869 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 5.1619. Min Range: -5.1619

Max Act: 5.0994. Min Act: -0.1700

Data Index: 152024 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 5.1619. Min Range: -5.1619

Max Act: 5.0682. Min Act: -0.1700

Data Index: 614354 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 5.1619. Min Range: -5.1619

Max Act: 5.0369. Min Act: -0.1700

Data Index: 145068 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 5.1619. Min Range: -5.1619

Max Act: 5.0682. Min Act: -0.1700

Data Index: 613128 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 5.1619. Min Range: -5.1619

Max Act: 5.0057. Min Act: -0.1700

Data Index: 858186 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 5.1619. Min Range: -5.1619

Max Act: 4.9744. Min Act: -0.1700

Data Index: 1349415 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 5.1619. Min Range: -5.1619

Max Act: 5.0057. Min Act: -0.1700

Data Index: 496400 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 5.1619. Min Range: -5.1619

Max Act: 4.9744. Min Act: -0.1700

Data Index: 916406 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 5.1619. Min Range: -5.1619

Max Act: 4.9744. Min Act: -0.1700

Data Index: 756226 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 5.1619. Min Range: -5.1619

Max Act: 4.9432. Min Act: -0.1700

Data Index: 440069 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 5.1619. Min Range: -5.1619

Max Act: 4.9744. Min Act: -0.1700

Data Index: 808271 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 5.1619. Min Range: -5.1619

Max Act: 4.9432. Min Act: -0.1700

Data Index: 435841 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 5.1619. Min Range: -5.1619

Max Act: 4.9432. Min Act: -0.1700

Data Index: 59421 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 5.1619. Min Range: -5.1619

Max Act: 4.9432. Min Act: -0.1700

Data Index: 393005 (C4 (Web Text))

Max Activating Token Index: 460