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

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

Neuron 1602 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: 3.2035. Min Range: -3.2035

Max Act: 3.2035. Min Act: -0.1700

Data Index: 965785 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.1563. Min Act: -0.1700

Data Index: 1104716 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.1721. Min Act: -0.1700

Data Index: 1118746 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.1563. Min Act: -0.1700

Data Index: 587897 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.1563. Min Act: -0.1700

Data Index: 1269396 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.1406. Min Act: -0.1700

Data Index: 260139 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.1091. Min Act: -0.1700

Data Index: 1257086 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.1091. Min Act: -0.1700

Data Index: 1263724 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.0933. Min Act: -0.1700

Data Index: 728349 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.0933. Min Act: -0.1700

Data Index: 932720 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.0933. Min Act: -0.1700

Data Index: 461270 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.1091. Min Act: -0.1700

Data Index: 921559 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.0933. Min Act: -0.1700

Data Index: 989214 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.0933. Min Act: -0.1700

Data Index: 204688 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.0775. Min Act: -0.1700

Data Index: 682386 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.0775. Min Act: -0.1700

Data Index: 206296 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.0617. Min Act: -0.1700

Data Index: 333666 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.0460. Min Act: -0.1700

Data Index: 284838 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.0775. Min Act: -0.1700

Data Index: 104455 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 3.2035. Min Range: -3.2035

Max Act: 3.0460. Min Act: -0.1700

Data Index: 54980 (C4 (Web Text))

Max Activating Token Index: 16