Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1800. Min Range: -1.1800
Max Act: 1.1800. Min Act: -0.1700
Data Index: 7833812 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1800. Min Range: -1.1800
Max Act: 1.1800. Min Act: -0.1700
Data Index: 5911884 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9617. Min Act: -0.1687
Data Index: 4007892 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9617. Min Act: -0.1700
Data Index: 6199900 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9617. Min Act: -0.1700
Data Index: 2772697 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9617. Min Act: -0.1685
Data Index: 4620560 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9617. Min Act: -0.1699
Data Index: 5994869 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9617. Min Act: -0.1700
Data Index: 7277023 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9617. Min Act: -0.1700
Data Index: 7243533 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9617. Min Act: -0.1698
Data Index: 8257764 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9617. Min Act: -0.1700
Data Index: 7623368 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9273. Min Act: -0.1690
Data Index: 1258213 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9101. Min Act: -0.1700
Data Index: 5293307 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9273. Min Act: -0.1700
Data Index: 6792340 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9101. Min Act: -0.1700
Data Index: 685193 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9187. Min Act: -0.1700
Data Index: 5361420 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9187. Min Act: -0.1688
Data Index: 3857950 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9187. Min Act: -0.1700
Data Index: 6544798 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9187. Min Act: -0.1544
Data Index: 2938360 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1800. Min Range: -1.1800
Max Act: 0.9101. Min Act: -0.1700
Data Index: 6317929 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19