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

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

Neuron 1052 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: 3.3982. Min Range: -3.3982

Max Act: 3.3982. Min Act: -0.1700

Data Index: 173776 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.3668. Min Act: -0.1700

Data Index: 542965 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.3197. Min Act: -0.1700

Data Index: 1299374 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.2883. Min Act: -0.1700

Data Index: 890989 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.2883. Min Act: -0.1700

Data Index: 293769 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.2411. Min Act: -0.1700

Data Index: 413058 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.2097. Min Act: -0.1700

Data Index: 223301 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.2097. Min Act: -0.1700

Data Index: 520655 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.2254. Min Act: -0.1700

Data Index: 1036154 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.2097. Min Act: -0.1700

Data Index: 217944 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.2254. Min Act: -0.1700

Data Index: 1142038 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.2097. Min Act: -0.1700

Data Index: 57117 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.1782. Min Act: -0.1700

Data Index: 445946 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.1782. Min Act: -0.1700

Data Index: 866053 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.1625. Min Act: -0.1700

Data Index: 866779 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.1625. Min Act: -0.1700

Data Index: 416675 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.1310. Min Act: -0.1700

Data Index: 1156818 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.1152. Min Act: -0.1700

Data Index: 547634 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.1310. Min Act: -0.1700

Data Index: 601053 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 3.3982. Min Range: -3.3982

Max Act: 3.1310. Min Act: -0.1700

Data Index: 791700 (C4 (Web Text))

Max Activating Token Index: 755