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

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

Neuron 619 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.1852. Min Act: -0.1700

Data Index: 941033 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.1852. Min Act: -0.1700

Data Index: 159711 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.1379. Min Act: -0.1700

Data Index: 805722 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.1379. Min Act: -0.1700

Data Index: 1157550 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.1064. Min Act: -0.1700

Data Index: 207790 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.1064. Min Act: -0.1700

Data Index: 479174 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.0749. Min Act: -0.1700

Data Index: 1084296 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.0906. Min Act: -0.1700

Data Index: 99973 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.0433. Min Act: -0.1700

Data Index: 937684 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.0906. Min Act: -0.1700

Data Index: 849896 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.0749. Min Act: -0.1700

Data Index: 141205 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.0749. Min Act: -0.1700

Data Index: 74397 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.0749. Min Act: -0.1700

Data Index: 106019 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.0433. Min Act: -0.1700

Data Index: 1149799 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.0591. Min Act: -0.1700

Data Index: 140138 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.0749. Min Act: -0.1700

Data Index: 1059148 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.0749. Min Act: -0.1700

Data Index: 997702 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.0275. Min Act: -0.1700

Data Index: 581912 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.0433. Min Act: -0.1700

Data Index: 1171134 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 3.1852. Min Range: -3.1852

Max Act: 3.0275. Min Act: -0.1700

Data Index: 931580 (C4 (Web Text))

Max Activating Token Index: 184