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

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

Neuron 1850 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.8105. Min Act: -0.1700

Data Index: 1285046 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.8105. Min Act: -0.1700

Data Index: 47392 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.6853. Min Act: -0.1700

Data Index: 683002 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.7479. Min Act: -0.1700

Data Index: 1073300 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.7792. Min Act: -0.1700

Data Index: 289622 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.7166. Min Act: -0.1700

Data Index: 705124 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.7166. Min Act: -0.1700

Data Index: 1349907 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.6540. Min Act: -0.1700

Data Index: 675628 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.6540. Min Act: -0.1700

Data Index: 1053909 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.6540. Min Act: -0.1700

Data Index: 489907 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.6540. Min Act: -0.1700

Data Index: 1214277 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.6227. Min Act: -0.1700

Data Index: 302334 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.6227. Min Act: -0.1700

Data Index: 375005 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.6227. Min Act: -0.1700

Data Index: 1153628 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.6227. Min Act: -0.1700

Data Index: 128563 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.6540. Min Act: -0.1700

Data Index: 543867 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.5914. Min Act: -0.1700

Data Index: 1319866 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.4974. Min Act: -0.1700

Data Index: 976692 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.5601. Min Act: -0.1700

Data Index: 492932 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 3.8105. Min Range: -3.8105

Max Act: 3.5601. Min Act: -0.1700

Data Index: 713962 (C4 (Web Text))

Max Activating Token Index: 514