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

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

Neuron 901 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.1851. Min Act: -0.1700

Data Index: 1624331 (Python Code)

Max Activating Token Index: 800

Text #1

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.1693. Min Act: -0.1700

Data Index: 781918 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.1379. Min Act: -0.1700

Data Index: 1290111 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.1379. Min Act: -0.1700

Data Index: 1527164 (Python Code)

Max Activating Token Index: 487

Text #4

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.1536. Min Act: -0.1700

Data Index: 1168307 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.1063. Min Act: -0.1700

Data Index: 948083 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.1221. Min Act: -0.1700

Data Index: 1504705 (Python Code)

Max Activating Token Index: 436

Text #7

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.1063. Min Act: -0.1700

Data Index: 421476 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.0748. Min Act: -0.1700

Data Index: 912626 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.0748. Min Act: -0.1700

Data Index: 1507142 (Python Code)

Max Activating Token Index: 445

Text #10

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.0274. Min Act: -0.1700

Data Index: 1624943 (Python Code)

Max Activating Token Index: 479

Text #11

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.0590. Min Act: -0.1700

Data Index: 358731 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.0590. Min Act: -0.1700

Data Index: 76011 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.0590. Min Act: -0.1700

Data Index: 696190 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.0116. Min Act: -0.1700

Data Index: 884552 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.0116. Min Act: -0.1700

Data Index: 1618703 (Python Code)

Max Activating Token Index: 570

Text #16

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.0432. Min Act: -0.1700

Data Index: 910311 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.0116. Min Act: -0.1700

Data Index: 635131 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.0274. Min Act: -0.1700

Data Index: 872662 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 3.1851. Min Range: -3.1851

Max Act: 3.0274. Min Act: -0.1700

Data Index: 1142193 (C4 (Web Text))

Max Activating Token Index: 611