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

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

Neuron 1226 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.6352. Min Act: -0.1700

Data Index: 1267195 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.4472. Min Act: -0.1700

Data Index: 1186405 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.4001. Min Act: -0.1700

Data Index: 213270 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.3845. Min Act: -0.1700

Data Index: 649097 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.3845. Min Act: -0.1700

Data Index: 592059 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.3531. Min Act: -0.1700

Data Index: 585308 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.3374. Min Act: -0.1700

Data Index: 1275480 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.3688. Min Act: -0.1700

Data Index: 942241 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.3845. Min Act: -0.1700

Data Index: 603109 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.3374. Min Act: -0.1700

Data Index: 1191456 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.3374. Min Act: -0.1700

Data Index: 918505 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.3531. Min Act: -0.1700

Data Index: 1342550 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.3374. Min Act: -0.1700

Data Index: 665783 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.3531. Min Act: -0.1700

Data Index: 385013 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.3374. Min Act: -0.1700

Data Index: 481532 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.3060. Min Act: -0.1700

Data Index: 1132296 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.3217. Min Act: -0.1700

Data Index: 966587 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.3217. Min Act: -0.1700

Data Index: 1069260 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.3374. Min Act: -0.1700

Data Index: 1231696 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.6352. Min Range: -3.6352

Max Act: 3.3060. Min Act: -0.1700

Data Index: 444366 (C4 (Web Text))

Max Activating Token Index: 594