Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2827 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2169. Min Range: -8.2169
Max Act: 8.2169. Min Act: -0.1700
Data Index: 581253 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2169. Min Range: -8.2169
Max Act: 8.1231. Min Act: -0.1700
Data Index: 7600126 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2169. Min Range: -8.2169
Max Act: 8.0294. Min Act: -0.1700
Data Index: 5096308 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.9669. Min Act: -0.1700
Data Index: 6547106 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.9356. Min Act: -0.1700
Data Index: 6341827 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.8731. Min Act: -0.1700
Data Index: 5133854 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.8106. Min Act: -0.1700
Data Index: 2941664 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.8106. Min Act: -0.1700
Data Index: 6371389 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.8419. Min Act: -0.1700
Data Index: 5610067 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.7794. Min Act: -0.1700
Data Index: 3234997 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.7794. Min Act: -0.1700
Data Index: 393264 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.7481. Min Act: -0.1700
Data Index: 5339936 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.7169. Min Act: -0.1700
Data Index: 5539670 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.7169. Min Act: -0.1700
Data Index: 4387885 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.6544. Min Act: -0.1700
Data Index: 4616309 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.6231. Min Act: -0.1700
Data Index: 3133233 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.5919. Min Act: -0.1700
Data Index: 3746848 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.5919. Min Act: -0.1700
Data Index: 2595160 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.5606. Min Act: -0.1700
Data Index: 5492964 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.5294. Min Act: -0.1700
Data Index: 2561712 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19