Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3608 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0452. Min Range: -2.0452
Max Act: 2.0284. Min Act: -0.1700
Data Index: 454569 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0452. Min Range: -2.0452
Max Act: 2.0452. Min Act: -0.1698
Data Index: 7459004 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.9777. Min Act: -0.1700
Data Index: 3400902 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.9608. Min Act: -0.1698
Data Index: 7459010 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.9608. Min Act: -0.1700
Data Index: 1209490 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.9608. Min Act: -0.1698
Data Index: 7459005 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.9268. Min Act: -0.1700
Data Index: 6571595 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.9438. Min Act: -0.1697
Data Index: 7459009 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.9268. Min Act: -0.1700
Data Index: 4472328 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.9268. Min Act: -0.1700
Data Index: 6494842 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.9268. Min Act: -0.1700
Data Index: 7459011 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.9268. Min Act: -0.1700
Data Index: 7459008 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.9268. Min Act: -0.1700
Data Index: 1167850 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.9268. Min Act: -0.1700
Data Index: 5094959 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.9098. Min Act: -0.1700
Data Index: 6471470 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.9098. Min Act: -0.1700
Data Index: 8232596 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.9268. Min Act: -0.1700
Data Index: 166387 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.9098. Min Act: -0.1700
Data Index: 6751976 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.8927. Min Act: -0.1700
Data Index: 2868693 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0452. Min Range: -2.0452
Max Act: 1.9098. Min Act: -0.1700
Data Index: 6159830 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19