Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1807 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.6324. Min Act: -0.1700

Data Index: 1068582 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.6011. Min Act: -0.1700

Data Index: 1150204 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.5854. Min Act: -0.1700

Data Index: 1040615 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.5854. Min Act: -0.1700

Data Index: 1276996 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.5384. Min Act: -0.1700

Data Index: 991102 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.5541. Min Act: -0.1700

Data Index: 1022409 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.5698. Min Act: -0.1700

Data Index: 1260658 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.5698. Min Act: -0.1700

Data Index: 853963 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.6011. Min Act: -0.1700

Data Index: 1152703 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.5541. Min Act: -0.1700

Data Index: 696480 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.5228. Min Act: -0.1700

Data Index: 778660 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.5228. Min Act: -0.1700

Data Index: 443161 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.5698. Min Act: -0.1700

Data Index: 124333 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.5384. Min Act: -0.1700

Data Index: 1205980 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.5854. Min Act: -0.1700

Data Index: 502125 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.5541. Min Act: -0.1700

Data Index: 979607 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.5228. Min Act: -0.1700

Data Index: 185225 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.5071. Min Act: -0.1700

Data Index: 656750 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.4914. Min Act: -0.1700

Data Index: 1066105 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 3.6324. Min Range: -3.6324

Max Act: 3.5541. Min Act: -0.1700

Data Index: 11824 (C4 (Web Text))

Max Activating Token Index: 922