Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1375 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.1726. Min Range: -4.1726

Max Act: 4.1726. Min Act: -0.1700

Data Index: 294916 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.9850. Min Act: -0.1700

Data Index: 849361 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.8756. Min Act: -0.1700

Data Index: 289815 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.8912. Min Act: -0.1700

Data Index: 1044963 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.8130. Min Act: -0.1700

Data Index: 918416 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.7974. Min Act: -0.1700

Data Index: 1282687 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.7817. Min Act: -0.1700

Data Index: 798005 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.7817. Min Act: -0.1700

Data Index: 1321409 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.7817. Min Act: -0.1700

Data Index: 1122676 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.7661. Min Act: -0.1700

Data Index: 531483 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.7817. Min Act: -0.1700

Data Index: 504516 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.7661. Min Act: -0.1700

Data Index: 950728 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.7661. Min Act: -0.1700

Data Index: 1329564 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.7348. Min Act: -0.1700

Data Index: 1034662 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.7348. Min Act: -0.1700

Data Index: 1048684 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.7192. Min Act: -0.1700

Data Index: 768261 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.7505. Min Act: -0.1700

Data Index: 75391 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.7505. Min Act: -0.1700

Data Index: 98817 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.6879. Min Act: -0.1700

Data Index: 879738 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 4.1726. Min Range: -4.1726

Max Act: 3.7192. Min Act: -0.1700

Data Index: 1218072 (C4 (Web Text))

Max Activating Token Index: 705