Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 453 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 5.2565. Min Range: -5.2565

Max Act: 5.2511. Min Act: -0.1700

Data Index: 186992 (Open Web Text)

Max Activating Token Index: 639

Text #1

Max Range: 5.2565. Min Range: -5.2565

Max Act: 5.2219. Min Act: -0.1700

Data Index: 3885255 (Open Web Text)

Max Activating Token Index: 740

Text #2

Max Range: 5.2565. Min Range: -5.2565

Max Act: 5.2565. Min Act: -0.1700

Data Index: 4633031 (Open Web Text)

Max Activating Token Index: 876

Text #3

Max Range: 5.2565. Min Range: -5.2565

Max Act: 5.1378. Min Act: -0.1700

Data Index: 1309957 (Open Web Text)

Max Activating Token Index: 827

Text #4

Max Range: 5.2565. Min Range: -5.2565

Max Act: 5.0809. Min Act: -0.1700

Data Index: 1737782 (Open Web Text)

Max Activating Token Index: 89

Text #5

Max Range: 5.2565. Min Range: -5.2565

Max Act: 5.1247. Min Act: -0.1700

Data Index: 5613825 (Open Web Text)

Max Activating Token Index: 208

Text #6

Max Range: 5.2565. Min Range: -5.2565

Max Act: 5.0720. Min Act: -0.1700

Data Index: 6783033 (Open Web Text)

Max Activating Token Index: 728

Text #7

Max Range: 5.2565. Min Range: -5.2565

Max Act: 5.0432. Min Act: -0.1700

Data Index: 5576639 (Open Web Text)

Max Activating Token Index: 652

Text #8

Max Range: 5.2565. Min Range: -5.2565

Max Act: 4.9561. Min Act: -0.1700

Data Index: 5114062 (Open Web Text)

Max Activating Token Index: 606

Text #9

Max Range: 5.2565. Min Range: -5.2565

Max Act: 4.9034. Min Act: -0.1700

Data Index: 3277027 (Open Web Text)

Max Activating Token Index: 493

Text #10

Max Range: 5.2565. Min Range: -5.2565

Max Act: 4.9167. Min Act: -0.1700

Data Index: 327853 (Open Web Text)

Max Activating Token Index: 142

Text #11

Max Range: 5.2565. Min Range: -5.2565

Max Act: 4.8827. Min Act: -0.1700

Data Index: 3774838 (Open Web Text)

Max Activating Token Index: 877

Text #12

Max Range: 5.2565. Min Range: -5.2565

Max Act: 4.9113. Min Act: -0.1700

Data Index: 692003 (Open Web Text)

Max Activating Token Index: 843

Text #13

Max Range: 5.2565. Min Range: -5.2565

Max Act: 4.8922. Min Act: -0.1700

Data Index: 6945646 (Open Web Text)

Max Activating Token Index: 644

Text #14

Max Range: 5.2565. Min Range: -5.2565

Max Act: 4.8730. Min Act: -0.1700

Data Index: 6150774 (Open Web Text)

Max Activating Token Index: 696

Text #15

Max Range: 5.2565. Min Range: -5.2565

Max Act: 4.9027. Min Act: -0.1700

Data Index: 3787872 (Open Web Text)

Max Activating Token Index: 218

Text #16

Max Range: 5.2565. Min Range: -5.2565

Max Act: 4.8648. Min Act: -0.1700

Data Index: 8372102 (Open Web Text)

Max Activating Token Index: 340

Text #17

Max Range: 5.2565. Min Range: -5.2565

Max Act: 4.8697. Min Act: -0.1700

Data Index: 7070855 (Open Web Text)

Max Activating Token Index: 617

Text #18

Max Range: 5.2565. Min Range: -5.2565

Max Act: 4.8843. Min Act: -0.1700

Data Index: 537024 (Open Web Text)

Max Activating Token Index: 999

Text #19

Max Range: 5.2565. Min Range: -5.2565

Max Act: 4.8460. Min Act: -0.1700

Data Index: 394114 (Open Web Text)

Max Activating Token Index: 676