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

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

Neuron 1995 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: 5.1389. Min Range: -5.1389

Max Act: 5.1389. Min Act: -0.1700

Data Index: 338704 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 5.1389. Min Range: -5.1389

Max Act: 5.1076. Min Act: -0.1700

Data Index: 652044 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 5.1389. Min Range: -5.1389

Max Act: 5.0764. Min Act: -0.1700

Data Index: 1173590 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 5.1389. Min Range: -5.1389

Max Act: 4.9826. Min Act: -0.1700

Data Index: 1114011 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 5.1389. Min Range: -5.1389

Max Act: 5.0139. Min Act: -0.1700

Data Index: 549856 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 5.1389. Min Range: -5.1389

Max Act: 5.0139. Min Act: -0.1700

Data Index: 505478 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 5.1389. Min Range: -5.1389

Max Act: 4.9826. Min Act: -0.1700

Data Index: 1337689 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 5.1389. Min Range: -5.1389

Max Act: 4.9514. Min Act: -0.1700

Data Index: 696924 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 5.1389. Min Range: -5.1389

Max Act: 4.9826. Min Act: -0.1700

Data Index: 364835 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 5.1389. Min Range: -5.1389

Max Act: 4.9826. Min Act: -0.1700

Data Index: 936446 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 5.1389. Min Range: -5.1389

Max Act: 4.9826. Min Act: -0.1700

Data Index: 915415 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 5.1389. Min Range: -5.1389

Max Act: 4.9826. Min Act: -0.1700

Data Index: 18806 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 5.1389. Min Range: -5.1389

Max Act: 4.9826. Min Act: -0.1700

Data Index: 116439 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 5.1389. Min Range: -5.1389

Max Act: 4.9826. Min Act: -0.1700

Data Index: 420793 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 5.1389. Min Range: -5.1389

Max Act: 4.9826. Min Act: -0.1700

Data Index: 1191277 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 5.1389. Min Range: -5.1389

Max Act: 4.9826. Min Act: -0.1700

Data Index: 973265 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 5.1389. Min Range: -5.1389

Max Act: 4.9514. Min Act: -0.1700

Data Index: 147832 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 5.1389. Min Range: -5.1389

Max Act: 5.0139. Min Act: -0.1700

Data Index: 1212745 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 5.1389. Min Range: -5.1389

Max Act: 4.9514. Min Act: -0.1700

Data Index: 388810 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 5.1389. Min Range: -5.1389

Max Act: 4.9514. Min Act: -0.1700

Data Index: 866612 (C4 (Web Text))

Max Activating Token Index: 655