Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0156. Min Range: -7.0156
Max Act: 7.0156. Min Act: -0.1700
Data Index: 5147078 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.8281. Min Act: -0.1700
Data Index: 5628950 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.8281. Min Act: -0.1700
Data Index: 6384976 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.8281. Min Act: -0.1700
Data Index: 4309491 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.7031. Min Act: -0.1700
Data Index: 5831302 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.6718. Min Act: -0.1700
Data Index: 1250523 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.7031. Min Act: -0.1700
Data Index: 61031 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.6718. Min Act: -0.1700
Data Index: 990525 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.6718. Min Act: -0.1700
Data Index: 6149743 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.6718. Min Act: -0.1700
Data Index: 957880 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.6718. Min Act: -0.1700
Data Index: 2777349 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.6718. Min Act: -0.1700
Data Index: 1295207 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.6718. Min Act: -0.1700
Data Index: 2388415 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.6406. Min Act: -0.1700
Data Index: 2090758 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.6406. Min Act: -0.1700
Data Index: 7454498 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.6406. Min Act: -0.1700
Data Index: 1278474 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.6406. Min Act: -0.1700
Data Index: 615371 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.5781. Min Act: -0.1700
Data Index: 2772930 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.5781. Min Act: -0.1700
Data Index: 2149595 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0156. Min Range: -7.0156
Max Act: 6.5781. Min Act: -0.1700
Data Index: 3804426 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19