Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2352 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.6889. Min Range: -9.6889
Max Act: 9.6889. Min Act: -0.1700
Data Index: 6002844 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6889. Min Range: -9.6889
Max Act: 9.5639. Min Act: -0.1700
Data Index: 3921373 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6889. Min Range: -9.6889
Max Act: 9.1889. Min Act: -0.1700
Data Index: 5546087 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6889. Min Range: -9.6889
Max Act: 9.1889. Min Act: -0.1700
Data Index: 3314161 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6889. Min Range: -9.6889
Max Act: 9.0639. Min Act: -0.1700
Data Index: 8118274 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6889. Min Range: -9.6889
Max Act: 9.0639. Min Act: -0.1700
Data Index: 8059001 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6889. Min Range: -9.6889
Max Act: 9.0014. Min Act: -0.1700
Data Index: 8004362 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6889. Min Range: -9.6889
Max Act: 9.0014. Min Act: -0.1700
Data Index: 3303597 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6889. Min Range: -9.6889
Max Act: 8.9389. Min Act: -0.1700
Data Index: 8118948 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6889. Min Range: -9.6889
Max Act: 8.8764. Min Act: -0.1700
Data Index: 8256413 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6889. Min Range: -9.6889
Max Act: 8.9389. Min Act: -0.1700
Data Index: 6117739 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6889. Min Range: -9.6889
Max Act: 8.8139. Min Act: -0.1700
Data Index: 8056197 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6889. Min Range: -9.6889
Max Act: 8.8764. Min Act: -0.1700
Data Index: 2171931 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6889. Min Range: -9.6889
Max Act: 8.8139. Min Act: -0.1700
Data Index: 7233531 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6889. Min Range: -9.6889
Max Act: 8.7514. Min Act: -0.1700
Data Index: 2523350 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6889. Min Range: -9.6889
Max Act: 8.7514. Min Act: -0.1700
Data Index: 2125738 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6889. Min Range: -9.6889
Max Act: 8.7514. Min Act: -0.1700
Data Index: 2886461 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6889. Min Range: -9.6889
Max Act: 8.7514. Min Act: -0.1700
Data Index: 8352686 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6889. Min Range: -9.6889
Max Act: 8.7514. Min Act: -0.1700
Data Index: 4053993 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6889. Min Range: -9.6889
Max Act: 8.6889. Min Act: -0.1700
Data Index: 3921310 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19