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

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

Neuron 293 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: 5.2879. Min Range: -5.2879

Max Act: 5.2879. Min Act: -0.1700

Data Index: 337080 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 5.2879. Min Range: -5.2879

Max Act: 5.2567. Min Act: -0.1700

Data Index: 341264 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 5.2879. Min Range: -5.2879

Max Act: 5.2567. Min Act: -0.1700

Data Index: 1329758 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 5.2879. Min Range: -5.2879

Max Act: 5.1317. Min Act: -0.1700

Data Index: 99485 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 5.2879. Min Range: -5.2879

Max Act: 5.1317. Min Act: -0.1700

Data Index: 860600 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 5.2879. Min Range: -5.2879

Max Act: 5.1629. Min Act: -0.1700

Data Index: 1063305 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 5.2879. Min Range: -5.2879

Max Act: 5.1629. Min Act: -0.1700

Data Index: 655335 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 5.2879. Min Range: -5.2879

Max Act: 5.1317. Min Act: -0.1700

Data Index: 850566 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 5.2879. Min Range: -5.2879

Max Act: 5.1317. Min Act: -0.1700

Data Index: 787462 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 5.2879. Min Range: -5.2879

Max Act: 5.0692. Min Act: -0.1700

Data Index: 429070 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 5.2879. Min Range: -5.2879

Max Act: 5.0379. Min Act: -0.1700

Data Index: 406648 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 5.2879. Min Range: -5.2879

Max Act: 5.1004. Min Act: -0.1700

Data Index: 702775 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 5.2879. Min Range: -5.2879

Max Act: 5.0379. Min Act: -0.1700

Data Index: 63011 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 5.2879. Min Range: -5.2879

Max Act: 5.0067. Min Act: -0.1700

Data Index: 625568 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 5.2879. Min Range: -5.2879

Max Act: 5.0379. Min Act: -0.1700

Data Index: 303323 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 5.2879. Min Range: -5.2879

Max Act: 5.0067. Min Act: -0.1700

Data Index: 1220996 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 5.2879. Min Range: -5.2879

Max Act: 4.9754. Min Act: -0.1700

Data Index: 831373 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 5.2879. Min Range: -5.2879

Max Act: 4.9754. Min Act: -0.1700

Data Index: 1059455 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 5.2879. Min Range: -5.2879

Max Act: 4.9754. Min Act: -0.1700

Data Index: 596513 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 5.2879. Min Range: -5.2879

Max Act: 4.9754. Min Act: -0.1700

Data Index: 922130 (C4 (Web Text))

Max Activating Token Index: 747