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

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

Neuron 1064 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.1038. Min Act: -0.1700

Data Index: 761517 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0880. Min Act: -0.1700

Data Index: 970115 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0407. Min Act: -0.1700

Data Index: 472569 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0249. Min Act: -0.1700

Data Index: 488526 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0407. Min Act: -0.1700

Data Index: 902194 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0091. Min Act: -0.1700

Data Index: 287960 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0249. Min Act: -0.1700

Data Index: 1232372 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0249. Min Act: -0.1700

Data Index: 1291327 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 3.1038. Min Range: -3.1038

Max Act: 3.0249. Min Act: -0.1700

Data Index: 1019933 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 3.1038. Min Range: -3.1038

Max Act: 2.9933. Min Act: -0.1700

Data Index: 106977 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 3.1038. Min Range: -3.1038

Max Act: 2.9775. Min Act: -0.1700

Data Index: 786175 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 3.1038. Min Range: -3.1038

Max Act: 2.9775. Min Act: -0.1700

Data Index: 647844 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 3.1038. Min Range: -3.1038

Max Act: 2.9933. Min Act: -0.1700

Data Index: 288001 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 3.1038. Min Range: -3.1038

Max Act: 2.9775. Min Act: -0.1700

Data Index: 297138 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 3.1038. Min Range: -3.1038

Max Act: 2.9617. Min Act: -0.1700

Data Index: 806828 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 3.1038. Min Range: -3.1038

Max Act: 2.9775. Min Act: -0.1700

Data Index: 77180 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 3.1038. Min Range: -3.1038

Max Act: 2.9617. Min Act: -0.1700

Data Index: 605504 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 3.1038. Min Range: -3.1038

Max Act: 2.9458. Min Act: -0.1700

Data Index: 703797 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 3.1038. Min Range: -3.1038

Max Act: 2.9775. Min Act: -0.1700

Data Index: 198847 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 3.1038. Min Range: -3.1038

Max Act: 2.9775. Min Act: -0.1700

Data Index: 296602 (C4 (Web Text))

Max Activating Token Index: 278