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

Dataset: Open Web Text

Neuron 1627 in Layer 1

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: 1.9773. Min Range: -1.9773

Max Act: 1.9773. Min Act: -0.1700

Data Index: 803890 (Open Web Text)

Max Activating Token Index: 42

Text #1

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.9571. Min Act: -0.1700

Data Index: 2052717 (Open Web Text)

Max Activating Token Index: 1010

Text #2

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.9346. Min Act: -0.1700

Data Index: 1687309 (Open Web Text)

Max Activating Token Index: 363

Text #3

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.8739. Min Act: -0.1700

Data Index: 255305 (Open Web Text)

Max Activating Token Index: 340

Text #4

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.8495. Min Act: -0.1700

Data Index: 5946853 (Open Web Text)

Max Activating Token Index: 638

Text #5

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.8353. Min Act: -0.1700

Data Index: 3341806 (Open Web Text)

Max Activating Token Index: 276

Text #6

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.8221. Min Act: -0.1700

Data Index: 2403956 (Open Web Text)

Max Activating Token Index: 745

Text #7

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.8288. Min Act: -0.1700

Data Index: 6525368 (Open Web Text)

Max Activating Token Index: 680

Text #8

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.8193. Min Act: -0.1700

Data Index: 1197195 (Open Web Text)

Max Activating Token Index: 268

Text #9

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.8074. Min Act: -0.1700

Data Index: 224881 (Open Web Text)

Max Activating Token Index: 376

Text #10

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.8038. Min Act: -0.1700

Data Index: 7985448 (Open Web Text)

Max Activating Token Index: 605

Text #11

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.7951. Min Act: -0.1700

Data Index: 4409143 (Open Web Text)

Max Activating Token Index: 987

Text #12

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.7864. Min Act: -0.1700

Data Index: 8817966 (Open Web Text)

Max Activating Token Index: 26

Text #13

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.7915. Min Act: -0.1700

Data Index: 685647 (Open Web Text)

Max Activating Token Index: 17

Text #14

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.7857. Min Act: -0.1700

Data Index: 6298977 (Open Web Text)

Max Activating Token Index: 1016

Text #15

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.7784. Min Act: -0.1700

Data Index: 7295640 (Open Web Text)

Max Activating Token Index: 664

Text #16

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.7865. Min Act: -0.1700

Data Index: 7208111 (Open Web Text)

Max Activating Token Index: 855

Text #17

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.7954. Min Act: -0.1700

Data Index: 3438456 (Open Web Text)

Max Activating Token Index: 815

Text #18

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.7862. Min Act: -0.1700

Data Index: 3009622 (Open Web Text)

Max Activating Token Index: 519

Text #19

Max Range: 1.9773. Min Range: -1.9773

Max Act: 1.7750. Min Act: -0.1700

Data Index: 6962534 (Open Web Text)

Max Activating Token Index: 675