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

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

Neuron 870 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1118. Min Range: -3.1118

Max Act: 3.1118. Min Act: -0.1700

Data Index: 909426 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 3.1118. Min Range: -3.1118

Max Act: 3.0645. Min Act: -0.1700

Data Index: 300833 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 3.1118. Min Range: -3.1118

Max Act: 3.0171. Min Act: -0.1700

Data Index: 403770 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.1118. Min Range: -3.1118

Max Act: 3.0329. Min Act: -0.1700

Data Index: 200741 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 3.1118. Min Range: -3.1118

Max Act: 3.0013. Min Act: -0.1700

Data Index: 1263578 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 3.1118. Min Range: -3.1118

Max Act: 3.0329. Min Act: -0.1700

Data Index: 714624 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 3.1118. Min Range: -3.1118

Max Act: 2.9855. Min Act: -0.1700

Data Index: 32291 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 3.1118. Min Range: -3.1118

Max Act: 2.9380. Min Act: -0.1700

Data Index: 158661 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 3.1118. Min Range: -3.1118

Max Act: 3.0013. Min Act: -0.1700

Data Index: 1352794 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 3.1118. Min Range: -3.1118

Max Act: 3.0013. Min Act: -0.1700

Data Index: 858852 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 3.1118. Min Range: -3.1118

Max Act: 2.9697. Min Act: -0.1700

Data Index: 900063 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 3.1118. Min Range: -3.1118

Max Act: 3.0013. Min Act: -0.1700

Data Index: 164993 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 3.1118. Min Range: -3.1118

Max Act: 2.9380. Min Act: -0.1700

Data Index: 61720 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 3.1118. Min Range: -3.1118

Max Act: 2.9222. Min Act: -0.1700

Data Index: 1256402 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 3.1118. Min Range: -3.1118

Max Act: 2.9222. Min Act: -0.1700

Data Index: 297680 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 3.1118. Min Range: -3.1118

Max Act: 2.9539. Min Act: -0.1700

Data Index: 145895 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 3.1118. Min Range: -3.1118

Max Act: 2.8905. Min Act: -0.1700

Data Index: 1200438 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 3.1118. Min Range: -3.1118

Max Act: 2.9539. Min Act: -0.1700

Data Index: 920765 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 3.1118. Min Range: -3.1118

Max Act: 2.9539. Min Act: -0.1700

Data Index: 299169 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 3.1118. Min Range: -3.1118

Max Act: 2.9539. Min Act: -0.1700

Data Index: 140233 (C4 (Web Text))

Max Activating Token Index: 645