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

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

Neuron 1450 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.2785. Min Act: -0.1700

Data Index: 106543 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1999. Min Act: -0.1700

Data Index: 1077838 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1842. Min Act: -0.1700

Data Index: 402163 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1999. Min Act: -0.1700

Data Index: 1315414 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1684. Min Act: -0.1700

Data Index: 1244675 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1684. Min Act: -0.1700

Data Index: 146482 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1684. Min Act: -0.1700

Data Index: 723186 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1369. Min Act: -0.1700

Data Index: 1004970 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1369. Min Act: -0.1700

Data Index: 216306 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1212. Min Act: -0.1700

Data Index: 1029398 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1369. Min Act: -0.1700

Data Index: 946983 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1212. Min Act: -0.1700

Data Index: 606076 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1212. Min Act: -0.1700

Data Index: 127832 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1369. Min Act: -0.1700

Data Index: 1197877 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1212. Min Act: -0.1700

Data Index: 588858 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1054. Min Act: -0.1700

Data Index: 691760 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1054. Min Act: -0.1700

Data Index: 631920 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1054. Min Act: -0.1700

Data Index: 612070 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1054. Min Act: -0.1700

Data Index: 836148 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 3.2785. Min Range: -3.2785

Max Act: 3.1054. Min Act: -0.1700

Data Index: 459395 (C4 (Web Text))

Max Activating Token Index: 13