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

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

Neuron 1384 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: 3.3840. Min Range: -3.3840

Max Act: 3.3840. Min Act: -0.1700

Data Index: 1252615 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.3683. Min Act: -0.1700

Data Index: 354468 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.3683. Min Act: -0.1700

Data Index: 10926 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.3369. Min Act: -0.1700

Data Index: 256085 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.3212. Min Act: -0.1700

Data Index: 981376 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.3055. Min Act: -0.1700

Data Index: 407197 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.3055. Min Act: -0.1700

Data Index: 816820 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.2741. Min Act: -0.1700

Data Index: 1329388 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.2898. Min Act: -0.1700

Data Index: 34708 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.2741. Min Act: -0.1700

Data Index: 1090975 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.2741. Min Act: -0.1700

Data Index: 646216 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.2427. Min Act: -0.1700

Data Index: 1114317 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.2427. Min Act: -0.1700

Data Index: 560038 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.2427. Min Act: -0.1700

Data Index: 401657 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.2427. Min Act: -0.1700

Data Index: 930030 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.2112. Min Act: -0.1700

Data Index: 1104584 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.2427. Min Act: -0.1700

Data Index: 1065923 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.2270. Min Act: -0.1700

Data Index: 92980 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.2270. Min Act: -0.1700

Data Index: 747225 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 3.3840. Min Range: -3.3840

Max Act: 3.2270. Min Act: -0.1700

Data Index: 971812 (C4 (Web Text))

Max Activating Token Index: 617