Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1863 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3370. Min Range: -8.3370
Max Act: 8.3370. Min Act: -0.1700
Data Index: 830639 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3370. Min Range: -8.3370
Max Act: 8.2745. Min Act: -0.1700
Data Index: 1944623 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3370. Min Range: -8.3370
Max Act: 8.0870. Min Act: -0.1700
Data Index: 4603943 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3370. Min Range: -8.3370
Max Act: 8.0870. Min Act: -0.1700
Data Index: 7321856 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3370. Min Range: -8.3370
Max Act: 7.9620. Min Act: -0.1700
Data Index: 4603949 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3370. Min Range: -8.3370
Max Act: 7.9620. Min Act: -0.1700
Data Index: 833289 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3370. Min Range: -8.3370
Max Act: 7.8995. Min Act: -0.1700
Data Index: 7399183 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3370. Min Range: -8.3370
Max Act: 7.8995. Min Act: -0.1700
Data Index: 7704949 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3370. Min Range: -8.3370
Max Act: 7.8370. Min Act: -0.1700
Data Index: 3415715 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3370. Min Range: -8.3370
Max Act: 7.8370. Min Act: -0.1700
Data Index: 4501914 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3370. Min Range: -8.3370
Max Act: 7.8370. Min Act: -0.1700
Data Index: 8478064 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3370. Min Range: -8.3370
Max Act: 7.7120. Min Act: -0.1700
Data Index: 4799942 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3370. Min Range: -8.3370
Max Act: 7.7120. Min Act: -0.1700
Data Index: 526651 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3370. Min Range: -8.3370
Max Act: 7.7120. Min Act: -0.1700
Data Index: 8227623 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3370. Min Range: -8.3370
Max Act: 7.7120. Min Act: -0.1700
Data Index: 903650 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3370. Min Range: -8.3370
Max Act: 7.6495. Min Act: -0.1700
Data Index: 2439206 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3370. Min Range: -8.3370
Max Act: 7.6495. Min Act: -0.1700
Data Index: 2730426 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3370. Min Range: -8.3370
Max Act: 7.6495. Min Act: -0.1700
Data Index: 123530 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3370. Min Range: -8.3370
Max Act: 7.5870. Min Act: -0.1700
Data Index: 6922582 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3370. Min Range: -8.3370
Max Act: 7.5870. Min Act: -0.1700
Data Index: 6261949 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19