Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1800 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.9637. Min Act: -0.1700

Data Index: 217565 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.9325. Min Act: -0.1700

Data Index: 242472 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.8387. Min Act: -0.1700

Data Index: 676132 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.9012. Min Act: -0.1700

Data Index: 128750 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.8387. Min Act: -0.1700

Data Index: 867267 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.8074. Min Act: -0.1700

Data Index: 1533425 (Python Code)

Max Activating Token Index: 150

Text #6

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.8387. Min Act: -0.1700

Data Index: 1147380 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.8387. Min Act: -0.1700

Data Index: 82522 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.8074. Min Act: -0.1700

Data Index: 153801 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.8387. Min Act: -0.1700

Data Index: 843329 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.8074. Min Act: -0.1700

Data Index: 102575 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.8074. Min Act: -0.1700

Data Index: 1273436 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7761. Min Act: -0.1700

Data Index: 724515 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7761. Min Act: -0.1700

Data Index: 609649 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7448. Min Act: -0.1700

Data Index: 923964 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.8074. Min Act: -0.1700

Data Index: 1148692 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.8074. Min Act: -0.1700

Data Index: 529708 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7761. Min Act: -0.1700

Data Index: 272628 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7135. Min Act: -0.1700

Data Index: 854321 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7135. Min Act: -0.1700

Data Index: 448295 (C4 (Web Text))

Max Activating Token Index: 902