Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1133 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.6237. Min Act: -0.1700

Data Index: 10084 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5454. Min Act: -0.1700

Data Index: 1228236 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5454. Min Act: -0.1700

Data Index: 1099815 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5454. Min Act: -0.1700

Data Index: 256935 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.4984. Min Act: -0.1700

Data Index: 411565 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5141. Min Act: -0.1700

Data Index: 559308 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.4827. Min Act: -0.1700

Data Index: 1355020 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.4827. Min Act: -0.1700

Data Index: 818326 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.4043. Min Act: -0.1700

Data Index: 1012609 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.3573. Min Act: -0.1700

Data Index: 382607 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.3573. Min Act: -0.1700

Data Index: 1284961 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.3573. Min Act: -0.1700

Data Index: 374487 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.4043. Min Act: -0.1700

Data Index: 257545 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.3730. Min Act: -0.1700

Data Index: 855393 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.4043. Min Act: -0.1700

Data Index: 483771 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.4514. Min Act: -0.1700

Data Index: 884819 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.3573. Min Act: -0.1700

Data Index: 232576 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.3416. Min Act: -0.1700

Data Index: 1214078 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.3416. Min Act: -0.1700

Data Index: 708232 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.3416. Min Act: -0.1700

Data Index: 743757 (C4 (Web Text))

Max Activating Token Index: 150