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

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

Neuron 842 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: 3.5363. Min Range: -3.5363

Max Act: 3.5363. Min Act: -0.1700

Data Index: 65677 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.3167. Min Act: -0.1700

Data Index: 553907 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.3010. Min Act: -0.1700

Data Index: 1269983 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.2067. Min Act: -0.1700

Data Index: 969232 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.2539. Min Act: -0.1700

Data Index: 89994 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.2067. Min Act: -0.1700

Data Index: 323714 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.1910. Min Act: -0.1700

Data Index: 953787 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.2539. Min Act: -0.1700

Data Index: 285459 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.1752. Min Act: -0.1700

Data Index: 734213 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.2067. Min Act: -0.1700

Data Index: 406440 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.1910. Min Act: -0.1700

Data Index: 564150 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.1595. Min Act: -0.1700

Data Index: 1091864 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.1595. Min Act: -0.1700

Data Index: 447978 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.1595. Min Act: -0.1700

Data Index: 1232532 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.1437. Min Act: -0.1700

Data Index: 558115 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.1595. Min Act: -0.1700

Data Index: 651509 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.1595. Min Act: -0.1700

Data Index: 1174999 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.1280. Min Act: -0.1700

Data Index: 983736 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.1437. Min Act: -0.1700

Data Index: 628780 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 3.5363. Min Range: -3.5363

Max Act: 3.1280. Min Act: -0.1700

Data Index: 492769 (C4 (Web Text))

Max Activating Token Index: 260