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

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

Neuron 1185 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.2780. Min Act: -0.1700

Data Index: 1329481 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.2624. Min Act: -0.1700

Data Index: 1093452 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.2155. Min Act: -0.1700

Data Index: 754581 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.1999. Min Act: -0.1700

Data Index: 1032206 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.1999. Min Act: -0.1700

Data Index: 1192501 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.1842. Min Act: -0.1700

Data Index: 870751 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.1530. Min Act: -0.1700

Data Index: 215655 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.1374. Min Act: -0.1700

Data Index: 466584 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.1061. Min Act: -0.1700

Data Index: 248925 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.0905. Min Act: -0.1700

Data Index: 689944 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.0592. Min Act: -0.1700

Data Index: 769187 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.1061. Min Act: -0.1700

Data Index: 1012668 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.0905. Min Act: -0.1700

Data Index: 540736 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.0749. Min Act: -0.1700

Data Index: 1128102 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.0905. Min Act: -0.1700

Data Index: 59223 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.0749. Min Act: -0.1700

Data Index: 537811 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.0749. Min Act: -0.1700

Data Index: 8461 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.0905. Min Act: -0.1700

Data Index: 189699 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.0749. Min Act: -0.1700

Data Index: 1213855 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 5.2780. Min Range: -5.2780

Max Act: 5.0592. Min Act: -0.1700

Data Index: 990065 (C4 (Web Text))

Max Activating Token Index: 706