Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3466 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1030. Min Range: -4.1030
Max Act: 4.1030. Min Act: -0.1700
Data Index: 7483144 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1030. Min Range: -4.1030
Max Act: 4.0092. Min Act: -0.1700
Data Index: 2902814 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.9780. Min Act: -0.1700
Data Index: 5018859 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.8686. Min Act: -0.1700
Data Index: 7218643 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.8373. Min Act: -0.1700
Data Index: 8716505 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.7435. Min Act: -0.1700
Data Index: 7128495 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.7435. Min Act: -0.1700
Data Index: 6787139 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.7122. Min Act: -0.1700
Data Index: 2695601 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.6652. Min Act: -0.1700
Data Index: 7143654 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.6496. Min Act: -0.1700
Data Index: 909599 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.6183. Min Act: -0.1700
Data Index: 5205894 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.6027. Min Act: -0.1700
Data Index: 3161038 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.5870. Min Act: -0.1700
Data Index: 1149691 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.5713. Min Act: -0.1700
Data Index: 4332132 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.5870. Min Act: -0.1700
Data Index: 6145931 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.5870. Min Act: -0.1700
Data Index: 2602140 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.5400. Min Act: -0.1700
Data Index: 7980880 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.5557. Min Act: -0.1700
Data Index: 6380714 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.5400. Min Act: -0.1700
Data Index: 3501965 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1030. Min Range: -4.1030
Max Act: 3.5400. Min Act: -0.1700
Data Index: 301790 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19