Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2470 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0267. Min Range: -9.0267
Max Act: 9.0267. Min Act: -0.1700
Data Index: 5007088 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.7142. Min Act: -0.1700
Data Index: 7065023 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.6517. Min Act: -0.1700
Data Index: 3239554 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.6517. Min Act: -0.1700
Data Index: 1709928 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.3392. Min Act: -0.1700
Data Index: 212438 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.2767. Min Act: -0.1700
Data Index: 7112280 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.2142. Min Act: -0.1700
Data Index: 3102827 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.2767. Min Act: -0.1700
Data Index: 5939360 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.2142. Min Act: -0.1700
Data Index: 4650259 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.2767. Min Act: -0.1700
Data Index: 357298 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.3392. Min Act: -0.1700
Data Index: 305806 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.2142. Min Act: -0.1700
Data Index: 1285453 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.2142. Min Act: -0.1700
Data Index: 5051797 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.1517. Min Act: -0.1700
Data Index: 5314770 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.0892. Min Act: -0.1700
Data Index: 5601892 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.1517. Min Act: -0.1700
Data Index: 825279 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.0892. Min Act: -0.1700
Data Index: 303002 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.0892. Min Act: -0.1700
Data Index: 7155013 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.0892. Min Act: -0.1700
Data Index: 69956 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0267. Min Range: -9.0267
Max Act: 8.0892. Min Act: -0.1700
Data Index: 4233377 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19