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

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

Neuron 1368 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: 3.2930. Min Range: -3.2930

Max Act: 3.2616. Min Act: -0.1700

Data Index: 346706 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.2930. Min Act: -0.1700

Data Index: 1270779 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.2773. Min Act: -0.1700

Data Index: 183367 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.2458. Min Act: -0.1700

Data Index: 55294 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.2458. Min Act: -0.1700

Data Index: 122624 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.2458. Min Act: -0.1700

Data Index: 626574 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.1514. Min Act: -0.1700

Data Index: 1138240 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.2458. Min Act: -0.1700

Data Index: 502397 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.1987. Min Act: -0.1700

Data Index: 853565 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.2301. Min Act: -0.1700

Data Index: 182532 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.1829. Min Act: -0.1700

Data Index: 419764 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.1987. Min Act: -0.1700

Data Index: 717162 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.1672. Min Act: -0.1700

Data Index: 1354201 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.1987. Min Act: -0.1700

Data Index: 541312 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.1672. Min Act: -0.1700

Data Index: 556942 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.1357. Min Act: -0.1700

Data Index: 593079 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.1042. Min Act: -0.1700

Data Index: 624708 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.0726. Min Act: -0.1700

Data Index: 184906 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.1514. Min Act: -0.1700

Data Index: 203876 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 3.2930. Min Range: -3.2930

Max Act: 3.1829. Min Act: -0.1700

Data Index: 88405 (C4 (Web Text))

Max Activating Token Index: 913