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

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

Neuron 1635 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: 3.3160. Min Range: -3.3160

Max Act: 3.3160. Min Act: -0.1700

Data Index: 754825 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1903. Min Act: -0.1700

Data Index: 6415 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1588. Min Act: -0.1700

Data Index: 717334 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1430. Min Act: -0.1700

Data Index: 1241354 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1745. Min Act: -0.1700

Data Index: 1035178 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1588. Min Act: -0.1700

Data Index: 451465 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1115. Min Act: -0.1700

Data Index: 982036 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.0957. Min Act: -0.1700

Data Index: 218529 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.0642. Min Act: -0.1700

Data Index: 107218 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.0800. Min Act: -0.1700

Data Index: 248759 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.0800. Min Act: -0.1700

Data Index: 985985 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.0800. Min Act: -0.1700

Data Index: 250812 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.0642. Min Act: -0.1700

Data Index: 260457 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.0642. Min Act: -0.1700

Data Index: 1151475 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.0800. Min Act: -0.1700

Data Index: 220641 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.0326. Min Act: -0.1700

Data Index: 749552 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.0326. Min Act: -0.1700

Data Index: 387545 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.0326. Min Act: -0.1700

Data Index: 1036261 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.0642. Min Act: -0.1700

Data Index: 1060411 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.0484. Min Act: -0.1700

Data Index: 534670 (C4 (Web Text))

Max Activating Token Index: 889