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

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

Neuron 418 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: 5.2699. Min Range: -5.2699

Max Act: 5.2699. Min Act: -0.1700

Data Index: 97041 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.2387. Min Act: -0.1700

Data Index: 79835 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.2387. Min Act: -0.1700

Data Index: 1202545 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.2387. Min Act: -0.1700

Data Index: 935038 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.2387. Min Act: -0.1700

Data Index: 428348 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.1762. Min Act: -0.1700

Data Index: 857841 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.1762. Min Act: -0.1700

Data Index: 1004832 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.1762. Min Act: -0.1700

Data Index: 23880 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.2074. Min Act: -0.1700

Data Index: 990759 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.1449. Min Act: -0.1700

Data Index: 679403 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.1762. Min Act: -0.1700

Data Index: 1085275 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.1137. Min Act: -0.1700

Data Index: 1020796 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.1762. Min Act: -0.1700

Data Index: 222100 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.2387. Min Act: -0.1700

Data Index: 857416 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.0512. Min Act: -0.1700

Data Index: 1093324 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.0199. Min Act: -0.1700

Data Index: 1203588 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.1137. Min Act: -0.1700

Data Index: 128967 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.0512. Min Act: -0.1700

Data Index: 213609 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 5.2699. Min Range: -5.2699

Max Act: 4.9887. Min Act: -0.1700

Data Index: 446045 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 5.2699. Min Range: -5.2699

Max Act: 5.0199. Min Act: -0.1700

Data Index: 415156 (C4 (Web Text))

Max Activating Token Index: 229