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

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

Neuron 1784 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: 3.0991. Min Range: -3.0991

Max Act: 3.0991. Min Act: -0.1700

Data Index: 949816 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0991. Min Act: -0.1700

Data Index: 1082805 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0676. Min Act: -0.1700

Data Index: 1172188 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0676. Min Act: -0.1700

Data Index: 615819 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0518. Min Act: -0.1700

Data Index: 1233090 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0202. Min Act: -0.1700

Data Index: 817375 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0360. Min Act: -0.1700

Data Index: 911737 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0202. Min Act: -0.1700

Data Index: 1246518 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0360. Min Act: -0.1700

Data Index: 83505 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0202. Min Act: -0.1700

Data Index: 1012236 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0202. Min Act: -0.1700

Data Index: 142248 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0044. Min Act: -0.1700

Data Index: 888305 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0044. Min Act: -0.1700

Data Index: 353694 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0360. Min Act: -0.1700

Data Index: 1266000 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0202. Min Act: -0.1700

Data Index: 946884 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0360. Min Act: -0.1700

Data Index: 604608 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0360. Min Act: -0.1700

Data Index: 698136 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0044. Min Act: -0.1700

Data Index: 977063 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 3.0991. Min Range: -3.0991

Max Act: 2.9886. Min Act: -0.1700

Data Index: 689976 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 3.0991. Min Range: -3.0991

Max Act: 3.0202. Min Act: -0.1700

Data Index: 814885 (C4 (Web Text))

Max Activating Token Index: 61