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

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

Neuron 112 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.6559. Min Act: -0.1700

Data Index: 744670 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.5619. Min Act: -0.1700

Data Index: 406078 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4993. Min Act: -0.1700

Data Index: 1310333 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4679. Min Act: -0.1700

Data Index: 1343950 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4993. Min Act: -0.1700

Data Index: 127648 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4993. Min Act: -0.1700

Data Index: 816297 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4993. Min Act: -0.1700

Data Index: 104161 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4993. Min Act: -0.1700

Data Index: 870179 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4993. Min Act: -0.1700

Data Index: 1089111 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4993. Min Act: -0.1700

Data Index: 914678 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4679. Min Act: -0.1700

Data Index: 18633 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4679. Min Act: -0.1700

Data Index: 313166 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4679. Min Act: -0.1700

Data Index: 750124 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4679. Min Act: -0.1700

Data Index: 1106625 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4366. Min Act: -0.1700

Data Index: 939537 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4366. Min Act: -0.1700

Data Index: 591852 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4366. Min Act: -0.1700

Data Index: 422508 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4366. Min Act: -0.1700

Data Index: 79495 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4366. Min Act: -0.1700

Data Index: 153088 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 3.6559. Min Range: -3.6559

Max Act: 3.4366. Min Act: -0.1700

Data Index: 76711 (C4 (Web Text))

Max Activating Token Index: 877