Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.8764. Min Act: -0.1700
Data Index: 1279289 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.8451. Min Act: -0.1700
Data Index: 1009161 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.6889. Min Act: -0.1700
Data Index: 4903840 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.4701. Min Act: -0.1700
Data Index: 6890688 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.3451. Min Act: -0.1700
Data Index: 4098995 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.2826. Min Act: -0.1700
Data Index: 6864740 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.3139. Min Act: -0.1700
Data Index: 5207184 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.2514. Min Act: -0.1700
Data Index: 6368787 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.2201. Min Act: -0.1700
Data Index: 8222170 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.2201. Min Act: -0.1700
Data Index: 8723024 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.1889. Min Act: -0.1700
Data Index: 906357 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.1889. Min Act: -0.1700
Data Index: 7226586 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.1264. Min Act: -0.1700
Data Index: 6352446 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.0951. Min Act: -0.1700
Data Index: 8083810 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.0951. Min Act: -0.1700
Data Index: 5798960 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.0326. Min Act: -0.1700
Data Index: 1320370 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.0639. Min Act: -0.1700
Data Index: 1642302 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.0326. Min Act: -0.1700
Data Index: 4682719 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.0326. Min Act: -0.1700
Data Index: 5428675 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8764. Min Range: -7.8764
Max Act: 7.0326. Min Act: -0.1700
Data Index: 6150366 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19