Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3892 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0238. Min Range: -6.0238
Max Act: 6.0238. Min Act: -0.1700
Data Index: 6218644 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.9925. Min Act: -0.1700
Data Index: 7335698 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.8363. Min Act: -0.1700
Data Index: 1128040 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.8675. Min Act: -0.1700
Data Index: 946140 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.7738. Min Act: -0.1700
Data Index: 8590840 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.7425. Min Act: -0.1700
Data Index: 1022583 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.7425. Min Act: -0.1700
Data Index: 7272623 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.7113. Min Act: -0.1700
Data Index: 8819736 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.7113. Min Act: -0.1700
Data Index: 1823873 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.6488. Min Act: -0.1700
Data Index: 273872 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.6800. Min Act: -0.1700
Data Index: 4313709 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.6175. Min Act: -0.1700
Data Index: 6847565 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.6175. Min Act: -0.1700
Data Index: 5714900 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.5863. Min Act: -0.1700
Data Index: 1128500 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.5863. Min Act: -0.1700
Data Index: 8574764 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.5550. Min Act: -0.1700
Data Index: 2170413 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.5863. Min Act: -0.1700
Data Index: 1128042 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.5863. Min Act: -0.1700
Data Index: 4488899 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.5863. Min Act: -0.1700
Data Index: 2091162 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0238. Min Range: -6.0238
Max Act: 5.5550. Min Act: -0.1700
Data Index: 47582 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19