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

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

Neuron 860 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: 5.2459. Min Range: -5.2459

Max Act: 5.2459. Min Act: -0.1700

Data Index: 74128 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 5.2459. Min Range: -5.2459

Max Act: 5.1834. Min Act: -0.1700

Data Index: 64216 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 5.2459. Min Range: -5.2459

Max Act: 5.1522. Min Act: -0.1700

Data Index: 474881 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 5.2459. Min Range: -5.2459

Max Act: 5.1209. Min Act: -0.1700

Data Index: 327209 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.2459. Min Range: -5.2459

Max Act: 5.0897. Min Act: -0.1700

Data Index: 623226 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 5.2459. Min Range: -5.2459

Max Act: 4.9959. Min Act: -0.1700

Data Index: 580710 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 5.2459. Min Range: -5.2459

Max Act: 4.9334. Min Act: -0.1700

Data Index: 540214 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 5.2459. Min Range: -5.2459

Max Act: 5.0116. Min Act: -0.1700

Data Index: 1311642 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 5.2459. Min Range: -5.2459

Max Act: 4.9647. Min Act: -0.1700

Data Index: 363678 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 5.2459. Min Range: -5.2459

Max Act: 4.9334. Min Act: -0.1700

Data Index: 584591 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 5.2459. Min Range: -5.2459

Max Act: 4.9334. Min Act: -0.1700

Data Index: 712788 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 5.2459. Min Range: -5.2459

Max Act: 4.9959. Min Act: -0.1700

Data Index: 523037 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 5.2459. Min Range: -5.2459

Max Act: 4.9491. Min Act: -0.1700

Data Index: 815911 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 5.2459. Min Range: -5.2459

Max Act: 4.8397. Min Act: -0.1700

Data Index: 85610 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 5.2459. Min Range: -5.2459

Max Act: 4.9334. Min Act: -0.1700

Data Index: 499022 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 5.2459. Min Range: -5.2459

Max Act: 4.8709. Min Act: -0.1700

Data Index: 1262 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 5.2459. Min Range: -5.2459

Max Act: 4.8709. Min Act: -0.1700

Data Index: 43832 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 5.2459. Min Range: -5.2459

Max Act: 4.8709. Min Act: -0.1700

Data Index: 555660 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 5.2459. Min Range: -5.2459

Max Act: 4.8397. Min Act: -0.1700

Data Index: 673884 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 5.2459. Min Range: -5.2459

Max Act: 4.9647. Min Act: -0.1700

Data Index: 1114818 (C4 (Web Text))

Max Activating Token Index: 781