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

Dataset: Open Web Text

Neuron 931 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: 3.1924. Min Range: -3.1924

Max Act: 3.1924. Min Act: -0.1700

Data Index: 7613747 (Open Web Text)

Max Activating Token Index: 150

Text #1

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.1636. Min Act: -0.1700

Data Index: 8630441 (Open Web Text)

Max Activating Token Index: 197

Text #2

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.1492. Min Act: -0.1700

Data Index: 3773541 (Open Web Text)

Max Activating Token Index: 58

Text #3

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.1599. Min Act: -0.1700

Data Index: 5038210 (Open Web Text)

Max Activating Token Index: 502

Text #4

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.1454. Min Act: -0.1700

Data Index: 6847974 (Open Web Text)

Max Activating Token Index: 661

Text #5

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.1152. Min Act: -0.1700

Data Index: 5463006 (Open Web Text)

Max Activating Token Index: 667

Text #6

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.1310. Min Act: -0.1700

Data Index: 2946410 (Open Web Text)

Max Activating Token Index: 213

Text #7

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.1255. Min Act: -0.1700

Data Index: 62935 (Open Web Text)

Max Activating Token Index: 256

Text #8

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.0980. Min Act: -0.1700

Data Index: 3497526 (Open Web Text)

Max Activating Token Index: 350

Text #9

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.0602. Min Act: -0.1700

Data Index: 679940 (Open Web Text)

Max Activating Token Index: 495

Text #10

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.1250. Min Act: -0.1700

Data Index: 1269901 (Open Web Text)

Max Activating Token Index: 556

Text #11

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.1055. Min Act: -0.1700

Data Index: 5619985 (Open Web Text)

Max Activating Token Index: 818

Text #12

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.0926. Min Act: -0.1700

Data Index: 8651594 (Open Web Text)

Max Activating Token Index: 781

Text #13

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.1003. Min Act: -0.1700

Data Index: 4860944 (Open Web Text)

Max Activating Token Index: 235

Text #14

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.0675. Min Act: -0.1700

Data Index: 3696047 (Open Web Text)

Max Activating Token Index: 440

Text #15

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.1197. Min Act: -0.1700

Data Index: 8502420 (Open Web Text)

Max Activating Token Index: 330

Text #16

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.0699. Min Act: -0.1700

Data Index: 5506135 (Open Web Text)

Max Activating Token Index: 57

Text #17

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.0755. Min Act: -0.1700

Data Index: 360872 (Open Web Text)

Max Activating Token Index: 228

Text #18

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.0997. Min Act: -0.1700

Data Index: 3766891 (Open Web Text)

Max Activating Token Index: 1017

Text #19

Max Range: 3.1924. Min Range: -3.1924

Max Act: 3.0605. Min Act: -0.1700

Data Index: 6452704 (Open Web Text)

Max Activating Token Index: 253