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

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

Neuron 887 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: 3.6478. Min Range: -3.6478

Max Act: 3.6165. Min Act: -0.1700

Data Index: 293039 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.6478. Min Act: -0.1700

Data Index: 1172186 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.5852. Min Act: -0.1700

Data Index: 1347943 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.6165. Min Act: -0.1700

Data Index: 965261 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.5852. Min Act: -0.1700

Data Index: 1309249 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.5852. Min Act: -0.1700

Data Index: 234622 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.5852. Min Act: -0.1700

Data Index: 773914 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.5852. Min Act: -0.1700

Data Index: 1094415 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.5539. Min Act: -0.1700

Data Index: 1331802 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.5539. Min Act: -0.1700

Data Index: 1239167 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.5539. Min Act: -0.1700

Data Index: 486917 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.5539. Min Act: -0.1700

Data Index: 978705 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.5539. Min Act: -0.1700

Data Index: 667315 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.5382. Min Act: -0.1700

Data Index: 778514 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.5382. Min Act: -0.1700

Data Index: 48019 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.5382. Min Act: -0.1700

Data Index: 1108700 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.5539. Min Act: -0.1700

Data Index: 1326902 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.5539. Min Act: -0.1700

Data Index: 999222 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.5382. Min Act: -0.1700

Data Index: 307762 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 3.6478. Min Range: -3.6478

Max Act: 3.5069. Min Act: -0.1700

Data Index: 150811 (C4 (Web Text))

Max Activating Token Index: 619