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

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

Neuron 1005 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3467. Min Range: -5.3467

Max Act: 5.3467. Min Act: -0.1700

Data Index: 129325 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 5.3467. Min Range: -5.3467

Max Act: 5.3467. Min Act: -0.1700

Data Index: 722527 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 5.3467. Min Range: -5.3467

Max Act: 5.2217. Min Act: -0.1700

Data Index: 1046510 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 5.3467. Min Range: -5.3467

Max Act: 5.0654. Min Act: -0.1700

Data Index: 389988 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 5.3467. Min Range: -5.3467

Max Act: 5.0967. Min Act: -0.1700

Data Index: 1188886 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 5.3467. Min Range: -5.3467

Max Act: 5.0654. Min Act: -0.1700

Data Index: 387825 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 5.3467. Min Range: -5.3467

Max Act: 5.0342. Min Act: -0.1700

Data Index: 695908 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 5.3467. Min Range: -5.3467

Max Act: 5.0342. Min Act: -0.1700

Data Index: 17320 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 5.3467. Min Range: -5.3467

Max Act: 5.0029. Min Act: -0.1700

Data Index: 1073741 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 5.3467. Min Range: -5.3467

Max Act: 5.0342. Min Act: -0.1700

Data Index: 479497 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 5.3467. Min Range: -5.3467

Max Act: 5.0029. Min Act: -0.1700

Data Index: 60668 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 5.3467. Min Range: -5.3467

Max Act: 5.0029. Min Act: -0.1700

Data Index: 298856 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 5.3467. Min Range: -5.3467

Max Act: 4.9717. Min Act: -0.1700

Data Index: 370399 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 5.3467. Min Range: -5.3467

Max Act: 5.0029. Min Act: -0.1700

Data Index: 1141010 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 5.3467. Min Range: -5.3467

Max Act: 4.9404. Min Act: -0.1700

Data Index: 976316 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 5.3467. Min Range: -5.3467

Max Act: 5.0029. Min Act: -0.1700

Data Index: 304476 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 5.3467. Min Range: -5.3467

Max Act: 4.9404. Min Act: -0.1700

Data Index: 69522 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 5.3467. Min Range: -5.3467

Max Act: 4.9717. Min Act: -0.1700

Data Index: 399860 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 5.3467. Min Range: -5.3467

Max Act: 4.9404. Min Act: -0.1700

Data Index: 696028 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 5.3467. Min Range: -5.3467

Max Act: 4.8779. Min Act: -0.1700

Data Index: 24524 (C4 (Web Text))

Max Activating Token Index: 936