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

Dataset: Open Web Text

Neuron 639 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: 3.0127. Min Range: -3.0127

Max Act: 3.0127. Min Act: -0.1700

Data Index: 1146624 (Open Web Text)

Max Activating Token Index: 586

Text #1

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.9650. Min Act: -0.1700

Data Index: 58473 (Open Web Text)

Max Activating Token Index: 556

Text #2

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.9519. Min Act: -0.1700

Data Index: 8616443 (Open Web Text)

Max Activating Token Index: 197

Text #3

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.9313. Min Act: -0.1700

Data Index: 6084279 (Open Web Text)

Max Activating Token Index: 461

Text #4

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.9270. Min Act: -0.1700

Data Index: 6736715 (Open Web Text)

Max Activating Token Index: 401

Text #5

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.9305. Min Act: -0.1700

Data Index: 5741249 (Open Web Text)

Max Activating Token Index: 699

Text #6

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.9251. Min Act: -0.1700

Data Index: 1946538 (Open Web Text)

Max Activating Token Index: 831

Text #7

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.8759. Min Act: -0.1700

Data Index: 1777652 (Open Web Text)

Max Activating Token Index: 945

Text #8

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.8990. Min Act: -0.1700

Data Index: 1364112 (Open Web Text)

Max Activating Token Index: 423

Text #9

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.8624. Min Act: -0.1700

Data Index: 5756700 (Open Web Text)

Max Activating Token Index: 527

Text #10

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.8735. Min Act: -0.1700

Data Index: 8003516 (Open Web Text)

Max Activating Token Index: 827

Text #11

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.8627. Min Act: -0.1700

Data Index: 4430161 (Open Web Text)

Max Activating Token Index: 229

Text #12

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.8482. Min Act: -0.1700

Data Index: 1677897 (Open Web Text)

Max Activating Token Index: 79

Text #13

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.8331. Min Act: -0.1700

Data Index: 3100009 (Open Web Text)

Max Activating Token Index: 34

Text #14

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.8012. Min Act: -0.1700

Data Index: 4516202 (Open Web Text)

Max Activating Token Index: 470

Text #15

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.8333. Min Act: -0.1700

Data Index: 4064903 (Open Web Text)

Max Activating Token Index: 975

Text #16

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.8132. Min Act: -0.1700

Data Index: 531071 (Open Web Text)

Max Activating Token Index: 787

Text #17

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.8418. Min Act: -0.1700

Data Index: 5214764 (Open Web Text)

Max Activating Token Index: 889

Text #18

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.8320. Min Act: -0.1700

Data Index: 6416592 (Open Web Text)

Max Activating Token Index: 815

Text #19

Max Range: 3.0127. Min Range: -3.0127

Max Act: 2.8131. Min Act: -0.1700

Data Index: 1118149 (Open Web Text)

Max Activating Token Index: 421