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

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

Neuron 305 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: 3.0914. Min Range: -3.0914

Max Act: 3.0914. Min Act: -0.1700

Data Index: 324406 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 3.0914. Min Range: -3.0914

Max Act: 3.0914. Min Act: -0.1700

Data Index: 814013 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 3.0914. Min Range: -3.0914

Max Act: 3.0599. Min Act: -0.1700

Data Index: 577697 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 3.0914. Min Range: -3.0914

Max Act: 3.0441. Min Act: -0.1700

Data Index: 649014 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 3.0914. Min Range: -3.0914

Max Act: 3.0283. Min Act: -0.1700

Data Index: 429061 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 3.0914. Min Range: -3.0914

Max Act: 3.0125. Min Act: -0.1700

Data Index: 728866 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 3.0914. Min Range: -3.0914

Max Act: 3.0599. Min Act: -0.1700

Data Index: 1306402 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 3.0914. Min Range: -3.0914

Max Act: 3.0441. Min Act: -0.1700

Data Index: 1251633 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 3.0914. Min Range: -3.0914

Max Act: 3.0441. Min Act: -0.1700

Data Index: 838135 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 3.0914. Min Range: -3.0914

Max Act: 3.0283. Min Act: -0.1700

Data Index: 1022986 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 3.0914. Min Range: -3.0914

Max Act: 3.0441. Min Act: -0.1700

Data Index: 595201 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 3.0914. Min Range: -3.0914

Max Act: 3.0283. Min Act: -0.1700

Data Index: 1194541 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 3.0914. Min Range: -3.0914

Max Act: 3.0283. Min Act: -0.1700

Data Index: 1293494 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 3.0914. Min Range: -3.0914

Max Act: 3.0125. Min Act: -0.1700

Data Index: 25507 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 3.0914. Min Range: -3.0914

Max Act: 3.0125. Min Act: -0.1700

Data Index: 1223556 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 3.0914. Min Range: -3.0914

Max Act: 2.9967. Min Act: -0.1700

Data Index: 668854 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 3.0914. Min Range: -3.0914

Max Act: 3.0125. Min Act: -0.1700

Data Index: 1029794 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 3.0914. Min Range: -3.0914

Max Act: 3.0283. Min Act: -0.1700

Data Index: 1122602 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 3.0914. Min Range: -3.0914

Max Act: 3.0125. Min Act: -0.1700

Data Index: 462607 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 3.0914. Min Range: -3.0914

Max Act: 2.9967. Min Act: -0.1700

Data Index: 505182 (C4 (Web Text))

Max Activating Token Index: 63