Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2840. Min Range: -7.2840
Max Act: 7.2840. Min Act: -0.1700
Data Index: 8087589 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2840. Min Range: -7.2840
Max Act: 7.2840. Min Act: -0.1700
Data Index: 3308687 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2840. Min Range: -7.2840
Max Act: 7.1902. Min Act: -0.1700
Data Index: 2208779 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2840. Min Range: -7.2840
Max Act: 7.1590. Min Act: -0.1700
Data Index: 2404850 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2840. Min Range: -7.2840
Max Act: 7.0965. Min Act: -0.1700
Data Index: 5211589 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2840. Min Range: -7.2840
Max Act: 7.0652. Min Act: -0.1700
Data Index: 5732600 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2840. Min Range: -7.2840
Max Act: 7.0652. Min Act: -0.1700
Data Index: 2208781 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2840. Min Range: -7.2840
Max Act: 7.0652. Min Act: -0.1700
Data Index: 8441540 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2840. Min Range: -7.2840
Max Act: 7.0652. Min Act: -0.1700
Data Index: 994332 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2840. Min Range: -7.2840
Max Act: 7.0652. Min Act: -0.1700
Data Index: 4746819 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2840. Min Range: -7.2840
Max Act: 7.0340. Min Act: -0.1700
Data Index: 2208773 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2840. Min Range: -7.2840
Max Act: 7.0340. Min Act: -0.1700
Data Index: 6926569 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2840. Min Range: -7.2840
Max Act: 7.0340. Min Act: -0.1700
Data Index: 2208776 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2840. Min Range: -7.2840
Max Act: 7.0027. Min Act: -0.1700
Data Index: 5464065 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2840. Min Range: -7.2840
Max Act: 7.0027. Min Act: -0.1700
Data Index: 8753863 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2840. Min Range: -7.2840
Max Act: 6.9715. Min Act: -0.1700
Data Index: 7990261 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2840. Min Range: -7.2840
Max Act: 6.9715. Min Act: -0.1700
Data Index: 2208775 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2840. Min Range: -7.2840
Max Act: 6.9715. Min Act: -0.1700
Data Index: 5437897 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2840. Min Range: -7.2840
Max Act: 6.9715. Min Act: -0.1700
Data Index: 5410347 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2840. Min Range: -7.2840
Max Act: 6.9402. Min Act: -0.1700
Data Index: 4933561 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19