Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.4823. Min Act: -0.1700
Data Index: 6794385 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.4499. Min Act: -0.1700
Data Index: 5055864 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.4499. Min Act: -0.1700
Data Index: 1452184 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.4499. Min Act: -0.1700
Data Index: 5899025 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.4173. Min Act: -0.1700
Data Index: 3541931 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.4173. Min Act: -0.1700
Data Index: 3880603 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.4173. Min Act: -0.1700
Data Index: 8234397 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.3847. Min Act: -0.1700
Data Index: 5659170 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.3683. Min Act: -0.1700
Data Index: 157012 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.3683. Min Act: -0.1700
Data Index: 4793813 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.3519. Min Act: -0.1700
Data Index: 7925252 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.3356. Min Act: -0.1700
Data Index: 3698 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.3356. Min Act: -0.1700
Data Index: 786842 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.3356. Min Act: -0.1697
Data Index: 8256857 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.3356. Min Act: -0.1700
Data Index: 3085163 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.3191. Min Act: -0.1700
Data Index: 3498789 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.3027. Min Act: -0.1700
Data Index: 5574035 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.3191. Min Act: -0.1700
Data Index: 7961072 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.3191. Min Act: -0.1700
Data Index: 5209035 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4823. Min Range: -2.4823
Max Act: 2.3191. Min Act: -0.1700
Data Index: 4562872 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19