Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4139 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.9180. Min Act: -0.1700
Data Index: 792149 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.4180. Min Act: -0.1700
Data Index: 5031271 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.3243. Min Act: -0.1700
Data Index: 622492 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.2930. Min Act: -0.1700
Data Index: 7893865 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.3243. Min Act: -0.1700
Data Index: 7592897 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.2305. Min Act: -0.1700
Data Index: 491686 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.2305. Min Act: -0.1700
Data Index: 416161 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.1993. Min Act: -0.1700
Data Index: 3706165 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.1993. Min Act: -0.1700
Data Index: 6232456 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.1993. Min Act: -0.1700
Data Index: 313990 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.1680. Min Act: -0.1700
Data Index: 5408105 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.1367. Min Act: -0.1700
Data Index: 974071 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.1680. Min Act: -0.1700
Data Index: 792148 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.1367. Min Act: -0.1700
Data Index: 8612764 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.1367. Min Act: -0.1700
Data Index: 6357457 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.1055. Min Act: -0.1700
Data Index: 3560208 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.0742. Min Act: -0.1700
Data Index: 2378984 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.0742. Min Act: -0.1700
Data Index: 4249679 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.0430. Min Act: -0.1700
Data Index: 7136740 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9180. Min Range: -4.9180
Max Act: 4.0430. Min Act: -0.1700
Data Index: 6060969 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19