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

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

Neuron 517 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.3094. Min Act: -0.1700

Data Index: 1011557 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.2780. Min Act: -0.1700

Data Index: 315645 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.2780. Min Act: -0.1700

Data Index: 294899 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.2780. Min Act: -0.1700

Data Index: 295974 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.2466. Min Act: -0.1700

Data Index: 363453 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.2308. Min Act: -0.1700

Data Index: 286324 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.2466. Min Act: -0.1700

Data Index: 1326205 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.2308. Min Act: -0.1700

Data Index: 1243294 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.2151. Min Act: -0.1700

Data Index: 369920 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.2308. Min Act: -0.1700

Data Index: 425012 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.2151. Min Act: -0.1700

Data Index: 796656 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.2308. Min Act: -0.1700

Data Index: 400183 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.2151. Min Act: -0.1700

Data Index: 17191 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.1994. Min Act: -0.1700

Data Index: 1272275 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.1994. Min Act: -0.1700

Data Index: 1326058 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.2151. Min Act: -0.1700

Data Index: 697005 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.1994. Min Act: -0.1700

Data Index: 1231808 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.2151. Min Act: -0.1700

Data Index: 535138 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.1836. Min Act: -0.1700

Data Index: 595947 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 3.3094. Min Range: -3.3094

Max Act: 3.1994. Min Act: -0.1700

Data Index: 879829 (C4 (Web Text))

Max Activating Token Index: 11