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

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

Neuron 827 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: 5.2444. Min Range: -5.2444

Max Act: 5.2444. Min Act: -0.1700

Data Index: 313821 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.2132. Min Act: -0.1700

Data Index: 1285329 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.1194. Min Act: -0.1700

Data Index: 1030334 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.2132. Min Act: -0.1700

Data Index: 481558 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.1194. Min Act: -0.1700

Data Index: 634069 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.1507. Min Act: -0.1700

Data Index: 608594 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.1507. Min Act: -0.1700

Data Index: 142209 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.0882. Min Act: -0.1700

Data Index: 759260 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.1819. Min Act: -0.1700

Data Index: 734973 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.1194. Min Act: -0.1700

Data Index: 462052 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.0882. Min Act: -0.1700

Data Index: 594503 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.0882. Min Act: -0.1700

Data Index: 762669 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.0882. Min Act: -0.1700

Data Index: 11633 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.1194. Min Act: -0.1700

Data Index: 561022 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.0569. Min Act: -0.1700

Data Index: 973834 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.0882. Min Act: -0.1700

Data Index: 1049038 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.0569. Min Act: -0.1700

Data Index: 322128 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 5.2444. Min Range: -5.2444

Max Act: 4.9944. Min Act: -0.1700

Data Index: 1053447 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.0569. Min Act: -0.1700

Data Index: 125776 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 5.2444. Min Range: -5.2444

Max Act: 5.0882. Min Act: -0.1700

Data Index: 945875 (C4 (Web Text))

Max Activating Token Index: 934