Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1744 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.1563. Min Range: -3.1563

Max Act: 3.1563. Min Act: -0.1700

Data Index: 1166539 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 3.1563. Min Range: -3.1563

Max Act: 3.1408. Min Act: -0.1700

Data Index: 532235 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 3.1563. Min Range: -3.1563

Max Act: 3.0264. Min Act: -0.1700

Data Index: 784164 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 3.1563. Min Range: -3.1563

Max Act: 3.0409. Min Act: -0.1700

Data Index: 967840 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 3.1563. Min Range: -3.1563

Max Act: 3.0152. Min Act: -0.1700

Data Index: 263001 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 3.1563. Min Range: -3.1563

Max Act: 3.0320. Min Act: -0.1700

Data Index: 1160541 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 3.1563. Min Range: -3.1563

Max Act: 3.0142. Min Act: -0.1700

Data Index: 597546 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 3.1563. Min Range: -3.1563

Max Act: 3.0176. Min Act: -0.1700

Data Index: 1286347 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 3.1563. Min Range: -3.1563

Max Act: 2.9965. Min Act: -0.1700

Data Index: 486952 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 3.1563. Min Range: -3.1563

Max Act: 2.9765. Min Act: -0.1700

Data Index: 1408942 (Python Code)

Max Activating Token Index: 833

Text #10

Max Range: 3.1563. Min Range: -3.1563

Max Act: 2.9679. Min Act: -0.1700

Data Index: 541855 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 3.1563. Min Range: -3.1563

Max Act: 2.9753. Min Act: -0.1700

Data Index: 795441 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 3.1563. Min Range: -3.1563

Max Act: 2.9613. Min Act: -0.1700

Data Index: 393604 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 3.1563. Min Range: -3.1563

Max Act: 2.9585. Min Act: -0.1700

Data Index: 32314 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 3.1563. Min Range: -3.1563

Max Act: 2.9751. Min Act: -0.1700

Data Index: 1184496 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 3.1563. Min Range: -3.1563

Max Act: 2.9646. Min Act: -0.1700

Data Index: 535522 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 3.1563. Min Range: -3.1563

Max Act: 2.9544. Min Act: -0.1700

Data Index: 753566 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 3.1563. Min Range: -3.1563

Max Act: 2.9517. Min Act: -0.1700

Data Index: 973564 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 3.1563. Min Range: -3.1563

Max Act: 2.9494. Min Act: -0.1700

Data Index: 1058570 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 3.1563. Min Range: -3.1563

Max Act: 2.9434. Min Act: -0.1700

Data Index: 922288 (C4 (Web Text))

Max Activating Token Index: 865