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

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

Neuron 738 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: 5.5247. Min Range: -5.5247

Max Act: 5.5247. Min Act: -0.1700

Data Index: 915034 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.4622. Min Act: -0.1700

Data Index: 43384 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.4622. Min Act: -0.1700

Data Index: 861573 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.4622. Min Act: -0.1700

Data Index: 343330 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.3685. Min Act: -0.1700

Data Index: 788884 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.3685. Min Act: -0.1700

Data Index: 1147997 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.2747. Min Act: -0.1700

Data Index: 462189 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.2747. Min Act: -0.1700

Data Index: 447900 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.3060. Min Act: -0.1700

Data Index: 411530 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.3060. Min Act: -0.1700

Data Index: 627578 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.3060. Min Act: -0.1700

Data Index: 194304 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.2435. Min Act: -0.1700

Data Index: 434506 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.2435. Min Act: -0.1700

Data Index: 816626 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.2435. Min Act: -0.1700

Data Index: 952446 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.2435. Min Act: -0.1700

Data Index: 975923 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.2747. Min Act: -0.1700

Data Index: 830633 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.1810. Min Act: -0.1700

Data Index: 712326 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.2435. Min Act: -0.1700

Data Index: 842872 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.1497. Min Act: -0.1700

Data Index: 573884 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 5.5247. Min Range: -5.5247

Max Act: 5.1497. Min Act: -0.1700

Data Index: 456497 (C4 (Web Text))

Max Activating Token Index: 375