Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3637 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3482. Min Range: -8.3482
Max Act: 8.3482. Min Act: -0.1700
Data Index: 7335000 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3482. Min Range: -8.3482
Max Act: 8.0982. Min Act: -0.1700
Data Index: 4998621 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3482. Min Range: -8.3482
Max Act: 8.0357. Min Act: -0.1700
Data Index: 5391792 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3482. Min Range: -8.3482
Max Act: 7.9107. Min Act: -0.1700
Data Index: 8135879 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3482. Min Range: -8.3482
Max Act: 7.8482. Min Act: -0.1700
Data Index: 4967868 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3482. Min Range: -8.3482
Max Act: 7.8482. Min Act: -0.1700
Data Index: 379250 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3482. Min Range: -8.3482
Max Act: 7.7857. Min Act: -0.1700
Data Index: 4846860 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3482. Min Range: -8.3482
Max Act: 7.8482. Min Act: -0.1700
Data Index: 4427044 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3482. Min Range: -8.3482
Max Act: 7.7232. Min Act: -0.1700
Data Index: 8428983 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3482. Min Range: -8.3482
Max Act: 7.6919. Min Act: -0.1700
Data Index: 8740701 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3482. Min Range: -8.3482
Max Act: 7.6919. Min Act: -0.1700
Data Index: 8095202 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3482. Min Range: -8.3482
Max Act: 7.6919. Min Act: -0.1700
Data Index: 5318810 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3482. Min Range: -8.3482
Max Act: 7.6919. Min Act: -0.1700
Data Index: 4912299 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3482. Min Range: -8.3482
Max Act: 7.6607. Min Act: -0.1700
Data Index: 2998552 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3482. Min Range: -8.3482
Max Act: 7.6294. Min Act: -0.1700
Data Index: 1048264 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3482. Min Range: -8.3482
Max Act: 7.6607. Min Act: -0.1700
Data Index: 4082330 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3482. Min Range: -8.3482
Max Act: 7.6294. Min Act: -0.1700
Data Index: 3028666 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3482. Min Range: -8.3482
Max Act: 7.5982. Min Act: -0.1700
Data Index: 4528364 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3482. Min Range: -8.3482
Max Act: 7.6294. Min Act: -0.1700
Data Index: 8532631 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3482. Min Range: -8.3482
Max Act: 7.5982. Min Act: -0.1700
Data Index: 6552281 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19