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

Dataset: Open Web Text

Neuron 435 in Layer 4

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: 4.0526. Min Range: -4.0526

Max Act: 4.0526. Min Act: -0.1700

Data Index: 2250007 (Open Web Text)

Max Activating Token Index: 899

Text #1

Max Range: 4.0526. Min Range: -4.0526

Max Act: 4.0190. Min Act: -0.1700

Data Index: 1906794 (Open Web Text)

Max Activating Token Index: 733

Text #2

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.9721. Min Act: -0.1700

Data Index: 6279382 (Open Web Text)

Max Activating Token Index: 35

Text #3

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.9404. Min Act: -0.1700

Data Index: 7945658 (Open Web Text)

Max Activating Token Index: 842

Text #4

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.9478. Min Act: -0.1700

Data Index: 4999776 (Open Web Text)

Max Activating Token Index: 407

Text #5

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.9175. Min Act: -0.1700

Data Index: 7592790 (Open Web Text)

Max Activating Token Index: 763

Text #6

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.8985. Min Act: -0.1700

Data Index: 838752 (Open Web Text)

Max Activating Token Index: 117

Text #7

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.8775. Min Act: -0.1700

Data Index: 2992130 (Open Web Text)

Max Activating Token Index: 843

Text #8

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.8806. Min Act: -0.1700

Data Index: 2992133 (Open Web Text)

Max Activating Token Index: 640

Text #9

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.8189. Min Act: -0.1700

Data Index: 1484478 (Open Web Text)

Max Activating Token Index: 579

Text #10

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.8152. Min Act: -0.1700

Data Index: 8411229 (Open Web Text)

Max Activating Token Index: 36

Text #11

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.8025. Min Act: -0.1700

Data Index: 6784741 (Open Web Text)

Max Activating Token Index: 560

Text #12

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.8364. Min Act: -0.1700

Data Index: 6586351 (Open Web Text)

Max Activating Token Index: 1012

Text #13

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.8081. Min Act: -0.1700

Data Index: 3077918 (Open Web Text)

Max Activating Token Index: 384

Text #14

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.8129. Min Act: -0.1700

Data Index: 7856 (Open Web Text)

Max Activating Token Index: 567

Text #15

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.7789. Min Act: -0.1700

Data Index: 2904356 (Open Web Text)

Max Activating Token Index: 532

Text #16

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.8102. Min Act: -0.1700

Data Index: 7546599 (Open Web Text)

Max Activating Token Index: 486

Text #17

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.7999. Min Act: -0.1700

Data Index: 8795394 (Open Web Text)

Max Activating Token Index: 914

Text #18

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.7921. Min Act: -0.1700

Data Index: 4534108 (Open Web Text)

Max Activating Token Index: 428

Text #19

Max Range: 4.0526. Min Range: -4.0526

Max Act: 3.7674. Min Act: -0.1700

Data Index: 4162173 (Open Web Text)

Max Activating Token Index: 550