Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2889 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7126. Min Range: -6.7126
Max Act: 6.7126. Min Act: -0.1700
Data Index: 6984661 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7126. Min Range: -6.7126
Max Act: 6.6813. Min Act: -0.1700
Data Index: 6753371 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7126. Min Range: -6.7126
Max Act: 6.3376. Min Act: -0.1700
Data Index: 3575687 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7126. Min Range: -6.7126
Max Act: 6.3376. Min Act: -0.1700
Data Index: 1997829 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7126. Min Range: -6.7126
Max Act: 6.2751. Min Act: -0.1700
Data Index: 6570668 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7126. Min Range: -6.7126
Max Act: 6.1813. Min Act: -0.1700
Data Index: 1676480 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7126. Min Range: -6.7126
Max Act: 6.1813. Min Act: -0.1700
Data Index: 1875354 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7126. Min Range: -6.7126
Max Act: 6.1188. Min Act: -0.1700
Data Index: 1751085 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7126. Min Range: -6.7126
Max Act: 6.0876. Min Act: -0.1700
Data Index: 8425397 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7126. Min Range: -6.7126
Max Act: 6.0563. Min Act: -0.1700
Data Index: 3721001 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7126. Min Range: -6.7126
Max Act: 6.0876. Min Act: -0.1700
Data Index: 6298345 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7126. Min Range: -6.7126
Max Act: 6.0251. Min Act: -0.1700
Data Index: 3640541 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7126. Min Range: -6.7126
Max Act: 6.0251. Min Act: -0.1700
Data Index: 7380198 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7126. Min Range: -6.7126
Max Act: 6.0251. Min Act: -0.1700
Data Index: 1751084 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7126. Min Range: -6.7126
Max Act: 5.9938. Min Act: -0.1700
Data Index: 7039774 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7126. Min Range: -6.7126
Max Act: 5.9626. Min Act: -0.1700
Data Index: 7572542 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7126. Min Range: -6.7126
Max Act: 5.9938. Min Act: -0.1700
Data Index: 2209444 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7126. Min Range: -6.7126
Max Act: 5.9001. Min Act: -0.1700
Data Index: 6128538 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7126. Min Range: -6.7126
Max Act: 5.9313. Min Act: -0.1700
Data Index: 5984065 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7126. Min Range: -6.7126
Max Act: 5.9313. Min Act: -0.1700
Data Index: 2499279 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19