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

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

Neuron 1804 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: 3.8914. Min Range: -3.8914

Max Act: 3.8914. Min Act: -0.1700

Data Index: 351894 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.8289. Min Act: -0.1700

Data Index: 948270 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.7350. Min Act: -0.1700

Data Index: 304167 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.7037. Min Act: -0.1700

Data Index: 804194 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.6098. Min Act: -0.1700

Data Index: 676089 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.6098. Min Act: -0.1700

Data Index: 70424 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.6411. Min Act: -0.1700

Data Index: 438143 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.6098. Min Act: -0.1700

Data Index: 721585 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.5472. Min Act: -0.1700

Data Index: 1083242 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.5785. Min Act: -0.1700

Data Index: 843070 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.6098. Min Act: -0.1700

Data Index: 657298 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.5472. Min Act: -0.1700

Data Index: 1329513 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.5159. Min Act: -0.1700

Data Index: 403457 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.5159. Min Act: -0.1700

Data Index: 72223 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.5159. Min Act: -0.1700

Data Index: 1320915 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.5785. Min Act: -0.1700

Data Index: 1225470 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.5472. Min Act: -0.1700

Data Index: 612902 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.5159. Min Act: -0.1700

Data Index: 295241 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.5785. Min Act: -0.1700

Data Index: 279606 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 3.8914. Min Range: -3.8914

Max Act: 3.5472. Min Act: -0.1700

Data Index: 747533 (C4 (Web Text))

Max Activating Token Index: 345