Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2396 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2189. Min Range: -4.2189
Max Act: 4.2189. Min Act: -0.1700
Data Index: 4450675 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2189. Min Range: -4.2189
Max Act: 4.0626. Min Act: -0.1700
Data Index: 5799213 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2189. Min Range: -4.2189
Max Act: 4.0001. Min Act: -0.1700
Data Index: 8085354 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2189. Min Range: -4.2189
Max Act: 3.8281. Min Act: -0.1700
Data Index: 5114002 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2189. Min Range: -4.2189
Max Act: 3.8125. Min Act: -0.1700
Data Index: 5114012 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2189. Min Range: -4.2189
Max Act: 3.7656. Min Act: -0.1700
Data Index: 5114007 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2189. Min Range: -4.2189
Max Act: 3.7499. Min Act: -0.1700
Data Index: 3207181 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2189. Min Range: -4.2189
Max Act: 3.7343. Min Act: -0.1700
Data Index: 734490 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2189. Min Range: -4.2189
Max Act: 3.7186. Min Act: -0.1700
Data Index: 5114005 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2189. Min Range: -4.2189
Max Act: 3.7030. Min Act: -0.1700
Data Index: 5810495 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2189. Min Range: -4.2189
Max Act: 3.7186. Min Act: -0.1700
Data Index: 5114011 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2189. Min Range: -4.2189
Max Act: 3.7343. Min Act: -0.1700
Data Index: 5114003 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2189. Min Range: -4.2189
Max Act: 3.7030. Min Act: -0.1700
Data Index: 5114006 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2189. Min Range: -4.2189
Max Act: 3.7030. Min Act: -0.1700
Data Index: 7250165 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2189. Min Range: -4.2189
Max Act: 3.7030. Min Act: -0.1700
Data Index: 5514225 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2189. Min Range: -4.2189
Max Act: 3.7030. Min Act: -0.1700
Data Index: 3316205 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2189. Min Range: -4.2189
Max Act: 3.7030. Min Act: -0.1700
Data Index: 1517650 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2189. Min Range: -4.2189
Max Act: 3.6874. Min Act: -0.1700
Data Index: 5114014 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2189. Min Range: -4.2189
Max Act: 3.6874. Min Act: -0.1700
Data Index: 1113252 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2189. Min Range: -4.2189
Max Act: 3.6874. Min Act: -0.1700
Data Index: 2504170 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19