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

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

Neuron 556 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: 8.5149. Min Range: -8.5149

Max Act: 8.5149. Min Act: -0.1700

Data Index: 469371 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 8.5149. Min Range: -8.5149

Max Act: 8.2649. Min Act: -0.1700

Data Index: 563469 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 8.5149. Min Range: -8.5149

Max Act: 8.2649. Min Act: -0.1700

Data Index: 917263 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 8.5149. Min Range: -8.5149

Max Act: 8.0774. Min Act: -0.1700

Data Index: 396788 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 8.5149. Min Range: -8.5149

Max Act: 8.1399. Min Act: -0.1700

Data Index: 1050819 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 8.5149. Min Range: -8.5149

Max Act: 8.1399. Min Act: -0.1700

Data Index: 880122 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 8.5149. Min Range: -8.5149

Max Act: 8.2024. Min Act: -0.1700

Data Index: 1022601 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 8.5149. Min Range: -8.5149

Max Act: 8.1399. Min Act: -0.1700

Data Index: 314784 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 8.5149. Min Range: -8.5149

Max Act: 8.1399. Min Act: -0.1700

Data Index: 63873 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 8.5149. Min Range: -8.5149

Max Act: 7.9524. Min Act: -0.1700

Data Index: 46490 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 8.5149. Min Range: -8.5149

Max Act: 7.7649. Min Act: -0.1700

Data Index: 434162 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 8.5149. Min Range: -8.5149

Max Act: 7.8899. Min Act: -0.1700

Data Index: 980411 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 8.5149. Min Range: -8.5149

Max Act: 7.8899. Min Act: -0.1700

Data Index: 646039 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 8.5149. Min Range: -8.5149

Max Act: 7.8899. Min Act: -0.1700

Data Index: 771762 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 8.5149. Min Range: -8.5149

Max Act: 7.8899. Min Act: -0.1700

Data Index: 772190 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 8.5149. Min Range: -8.5149

Max Act: 7.7024. Min Act: -0.1700

Data Index: 1028280 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 8.5149. Min Range: -8.5149

Max Act: 7.8274. Min Act: -0.1700

Data Index: 518440 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 8.5149. Min Range: -8.5149

Max Act: 7.7024. Min Act: -0.1700

Data Index: 686646 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 8.5149. Min Range: -8.5149

Max Act: 7.7024. Min Act: -0.1700

Data Index: 376793 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 8.5149. Min Range: -8.5149

Max Act: 7.6399. Min Act: -0.1700

Data Index: 500733 (C4 (Web Text))

Max Activating Token Index: 605