Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5652 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4164. Min Range: -8.4164
Max Act: 8.4164. Min Act: -0.1700
Data Index: 828606 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4164. Min Range: -8.4164
Max Act: 8.1039. Min Act: -0.1700
Data Index: 1541533 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4164. Min Range: -8.4164
Max Act: 8.1039. Min Act: -0.1700
Data Index: 7162679 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4164. Min Range: -8.4164
Max Act: 7.9164. Min Act: -0.1700
Data Index: 7902615 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4164. Min Range: -8.4164
Max Act: 7.7914. Min Act: -0.1700
Data Index: 5376421 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4164. Min Range: -8.4164
Max Act: 7.7289. Min Act: -0.1700
Data Index: 6806820 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4164. Min Range: -8.4164
Max Act: 7.6664. Min Act: -0.1700
Data Index: 8403781 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4164. Min Range: -8.4164
Max Act: 7.6039. Min Act: -0.1700
Data Index: 4527799 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4164. Min Range: -8.4164
Max Act: 7.6039. Min Act: -0.1700
Data Index: 3204952 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4164. Min Range: -8.4164
Max Act: 7.5727. Min Act: -0.1700
Data Index: 5425241 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4164. Min Range: -8.4164
Max Act: 7.6039. Min Act: -0.1700
Data Index: 6660786 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4164. Min Range: -8.4164
Max Act: 7.5727. Min Act: -0.1700
Data Index: 104676 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4164. Min Range: -8.4164
Max Act: 7.5727. Min Act: -0.1700
Data Index: 1364681 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4164. Min Range: -8.4164
Max Act: 7.5727. Min Act: -0.1700
Data Index: 97367 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4164. Min Range: -8.4164
Max Act: 7.5727. Min Act: -0.1700
Data Index: 3800495 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4164. Min Range: -8.4164
Max Act: 7.5727. Min Act: -0.1700
Data Index: 5705247 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4164. Min Range: -8.4164
Max Act: 7.5727. Min Act: -0.1700
Data Index: 279243 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4164. Min Range: -8.4164
Max Act: 7.5727. Min Act: -0.1700
Data Index: 3259649 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4164. Min Range: -8.4164
Max Act: 7.5414. Min Act: -0.1700
Data Index: 8599467 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4164. Min Range: -8.4164
Max Act: 7.5414. Min Act: -0.1700
Data Index: 4389930 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19