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

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

Neuron 883 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: 3.4051. Min Range: -3.4051

Max Act: 3.4051. Min Act: -0.1700

Data Index: 729816 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.2167. Min Act: -0.1700

Data Index: 746179 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.1537. Min Act: -0.1700

Data Index: 1160077 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.2009. Min Act: -0.1700

Data Index: 1404649 (Python Code)

Max Activating Token Index: 61

Text #4

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.1537. Min Act: -0.1700

Data Index: 1382484 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.2481. Min Act: -0.1700

Data Index: 110988 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.1852. Min Act: -0.1700

Data Index: 1315242 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.1695. Min Act: -0.1700

Data Index: 886296 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.1380. Min Act: -0.1700

Data Index: 1504255 (Python Code)

Max Activating Token Index: 376

Text #9

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.1380. Min Act: -0.1700

Data Index: 1193361 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.1537. Min Act: -0.1700

Data Index: 1490727 (Python Code)

Max Activating Token Index: 84

Text #11

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.1537. Min Act: -0.1700

Data Index: 355984 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.1380. Min Act: -0.1700

Data Index: 726214 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.1222. Min Act: -0.1700

Data Index: 1495570 (Python Code)

Max Activating Token Index: 845

Text #14

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.1537. Min Act: -0.1700

Data Index: 1517745 (Python Code)

Max Activating Token Index: 459

Text #15

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.1380. Min Act: -0.1700

Data Index: 1399902 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.0749. Min Act: -0.1700

Data Index: 274010 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.1222. Min Act: -0.1700

Data Index: 1049336 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.1537. Min Act: -0.1700

Data Index: 1511220 (Python Code)

Max Activating Token Index: 601

Text #19

Max Range: 3.4051. Min Range: -3.4051

Max Act: 3.0749. Min Act: -0.1700

Data Index: 1541976 (Python Code)

Max Activating Token Index: 558