Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2175 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0217. Min Range: -8.0217
Max Act: 8.0217. Min Act: -0.1700
Data Index: 5700339 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.8655. Min Act: -0.1700
Data Index: 8035748 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.8342. Min Act: -0.1700
Data Index: 3386316 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.7717. Min Act: -0.1700
Data Index: 2542496 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.7405. Min Act: -0.1700
Data Index: 568227 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.6780. Min Act: -0.1700
Data Index: 60613 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.6467. Min Act: -0.1700
Data Index: 3098588 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.6467. Min Act: -0.1700
Data Index: 2137533 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.6467. Min Act: -0.1700
Data Index: 6378374 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.6155. Min Act: -0.1700
Data Index: 5778356 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.5842. Min Act: -0.1700
Data Index: 5717308 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.5217. Min Act: -0.1700
Data Index: 7436602 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.5217. Min Act: -0.1700
Data Index: 3173087 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.4905. Min Act: -0.1700
Data Index: 4038206 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.4592. Min Act: -0.1700
Data Index: 4218129 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.4280. Min Act: -0.1700
Data Index: 5203047 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.4280. Min Act: -0.1700
Data Index: 2692758 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.4280. Min Act: -0.1700
Data Index: 7892233 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.4280. Min Act: -0.1700
Data Index: 3134033 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0217. Min Range: -8.0217
Max Act: 7.4280. Min Act: -0.1700
Data Index: 8457322 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19