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

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

Neuron 685 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: 3.6735. Min Range: -3.6735

Max Act: 3.6422. Min Act: -0.1700

Data Index: 384174 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.6735. Min Act: -0.1700

Data Index: 96010 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.5483. Min Act: -0.1700

Data Index: 1313606 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.5952. Min Act: -0.1700

Data Index: 1076426 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.5952. Min Act: -0.1700

Data Index: 1102456 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.5483. Min Act: -0.1700

Data Index: 834819 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.6265. Min Act: -0.1700

Data Index: 99515 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.5483. Min Act: -0.1700

Data Index: 1006352 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.5326. Min Act: -0.1700

Data Index: 114794 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.5326. Min Act: -0.1700

Data Index: 807865 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.5013. Min Act: -0.1700

Data Index: 63319 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.5483. Min Act: -0.1700

Data Index: 370991 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.5169. Min Act: -0.1700

Data Index: 714245 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.5013. Min Act: -0.1700

Data Index: 659461 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.5169. Min Act: -0.1700

Data Index: 1343136 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.5169. Min Act: -0.1700

Data Index: 674855 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.5326. Min Act: -0.1700

Data Index: 976846 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.5169. Min Act: -0.1700

Data Index: 597721 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.5326. Min Act: -0.1700

Data Index: 984091 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 3.6735. Min Range: -3.6735

Max Act: 3.4699. Min Act: -0.1700

Data Index: 1092641 (C4 (Web Text))

Max Activating Token Index: 568