Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2048 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2186. Min Range: -5.2186
Max Act: 5.2186. Min Act: -0.1700
Data Index: 6328164 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2186. Min Range: -5.2186
Max Act: 5.1561. Min Act: -0.1700
Data Index: 1741390 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2186. Min Range: -5.2186
Max Act: 5.0623. Min Act: -0.1700
Data Index: 1858666 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2186. Min Range: -5.2186
Max Act: 4.9998. Min Act: -0.1700
Data Index: 1946383 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2186. Min Range: -5.2186
Max Act: 4.9998. Min Act: -0.1700
Data Index: 5154894 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2186. Min Range: -5.2186
Max Act: 4.9686. Min Act: -0.1700
Data Index: 6012679 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2186. Min Range: -5.2186
Max Act: 4.9373. Min Act: -0.1700
Data Index: 8170207 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2186. Min Range: -5.2186
Max Act: 4.8748. Min Act: -0.1700
Data Index: 1351326 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2186. Min Range: -5.2186
Max Act: 4.9061. Min Act: -0.1700
Data Index: 515166 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2186. Min Range: -5.2186
Max Act: 4.9061. Min Act: -0.1700
Data Index: 4064246 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2186. Min Range: -5.2186
Max Act: 4.9061. Min Act: -0.1700
Data Index: 4551857 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2186. Min Range: -5.2186
Max Act: 4.8748. Min Act: -0.1700
Data Index: 455239 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2186. Min Range: -5.2186
Max Act: 4.8748. Min Act: -0.1700
Data Index: 6339450 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2186. Min Range: -5.2186
Max Act: 4.8748. Min Act: -0.1700
Data Index: 1025162 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2186. Min Range: -5.2186
Max Act: 4.8123. Min Act: -0.1700
Data Index: 332586 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2186. Min Range: -5.2186
Max Act: 4.8436. Min Act: -0.1700
Data Index: 7496145 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2186. Min Range: -5.2186
Max Act: 4.8436. Min Act: -0.1700
Data Index: 3288384 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2186. Min Range: -5.2186
Max Act: 4.8123. Min Act: -0.1700
Data Index: 1518010 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2186. Min Range: -5.2186
Max Act: 4.8123. Min Act: -0.1700
Data Index: 3134249 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2186. Min Range: -5.2186
Max Act: 4.8123. Min Act: -0.1700
Data Index: 4773123 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19