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

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

Neuron 1867 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0329. Min Range: -3.0329

Max Act: 3.0329. Min Act: -0.1700

Data Index: 1156446 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 3.0329. Min Range: -3.0329

Max Act: 3.0171. Min Act: -0.1700

Data Index: 173550 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 3.0329. Min Range: -3.0329

Max Act: 3.0013. Min Act: -0.1700

Data Index: 24163 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 3.0329. Min Range: -3.0329

Max Act: 3.0013. Min Act: -0.1700

Data Index: 39975 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 3.0329. Min Range: -3.0329

Max Act: 3.0013. Min Act: -0.1700

Data Index: 522667 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 3.0329. Min Range: -3.0329

Max Act: 2.9539. Min Act: -0.1700

Data Index: 118312 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 3.0329. Min Range: -3.0329

Max Act: 2.9855. Min Act: -0.1700

Data Index: 693871 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 3.0329. Min Range: -3.0329

Max Act: 2.9697. Min Act: -0.1700

Data Index: 103766 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 3.0329. Min Range: -3.0329

Max Act: 2.9855. Min Act: -0.1700

Data Index: 1221599 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 3.0329. Min Range: -3.0329

Max Act: 2.9855. Min Act: -0.1700

Data Index: 922995 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 3.0329. Min Range: -3.0329

Max Act: 2.9855. Min Act: -0.1700

Data Index: 101013 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 3.0329. Min Range: -3.0329

Max Act: 2.9697. Min Act: -0.1700

Data Index: 256390 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 3.0329. Min Range: -3.0329

Max Act: 2.9697. Min Act: -0.1700

Data Index: 441147 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 3.0329. Min Range: -3.0329

Max Act: 2.9539. Min Act: -0.1700

Data Index: 1236665 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 3.0329. Min Range: -3.0329

Max Act: 2.9380. Min Act: -0.1700

Data Index: 31070 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 3.0329. Min Range: -3.0329

Max Act: 2.9063. Min Act: -0.1700

Data Index: 299560 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 3.0329. Min Range: -3.0329

Max Act: 2.9063. Min Act: -0.1700

Data Index: 1343587 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 3.0329. Min Range: -3.0329

Max Act: 2.9063. Min Act: -0.1700

Data Index: 218142 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 3.0329. Min Range: -3.0329

Max Act: 2.8587. Min Act: -0.1700

Data Index: 843745 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 3.0329. Min Range: -3.0329

Max Act: 2.8587. Min Act: -0.1700

Data Index: 330610 (C4 (Web Text))

Max Activating Token Index: 455