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

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

Neuron 1872 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: 4.1261. Min Range: -4.1261

Max Act: 4.1261. Min Act: -0.1700

Data Index: 118277 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 4.1261. Min Range: -4.1261

Max Act: 4.0948. Min Act: -0.1700

Data Index: 39847 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 4.1261. Min Range: -4.1261

Max Act: 4.0636. Min Act: -0.1700

Data Index: 1309306 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.1261. Min Range: -4.1261

Max Act: 4.0010. Min Act: -0.1700

Data Index: 1214517 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 4.1261. Min Range: -4.1261

Max Act: 4.0010. Min Act: -0.1700

Data Index: 792544 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 4.1261. Min Range: -4.1261

Max Act: 3.9698. Min Act: -0.1700

Data Index: 668790 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.1261. Min Range: -4.1261

Max Act: 4.0010. Min Act: -0.1700

Data Index: 214590 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 4.1261. Min Range: -4.1261

Max Act: 3.9072. Min Act: -0.1700

Data Index: 76679 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 4.1261. Min Range: -4.1261

Max Act: 3.9385. Min Act: -0.1700

Data Index: 357986 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.1261. Min Range: -4.1261

Max Act: 3.9385. Min Act: -0.1700

Data Index: 1138115 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 4.1261. Min Range: -4.1261

Max Act: 3.9698. Min Act: -0.1700

Data Index: 249206 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 4.1261. Min Range: -4.1261

Max Act: 3.9072. Min Act: -0.1700

Data Index: 234187 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 4.1261. Min Range: -4.1261

Max Act: 3.9072. Min Act: -0.1700

Data Index: 603878 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 4.1261. Min Range: -4.1261

Max Act: 3.8447. Min Act: -0.1700

Data Index: 227183 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 4.1261. Min Range: -4.1261

Max Act: 3.8759. Min Act: -0.1700

Data Index: 650770 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.1261. Min Range: -4.1261

Max Act: 3.8759. Min Act: -0.1700

Data Index: 1000854 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.1261. Min Range: -4.1261

Max Act: 3.8759. Min Act: -0.1700

Data Index: 647768 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 4.1261. Min Range: -4.1261

Max Act: 3.9072. Min Act: -0.1700

Data Index: 125032 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.1261. Min Range: -4.1261

Max Act: 3.8759. Min Act: -0.1700

Data Index: 302503 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 4.1261. Min Range: -4.1261

Max Act: 3.8759. Min Act: -0.1700

Data Index: 579450 (C4 (Web Text))

Max Activating Token Index: 368