Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.8014. Min Act: -0.1700
Data Index: 5897898 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.7389. Min Act: -0.1700
Data Index: 30614 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.7389. Min Act: -0.1700
Data Index: 1245756 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.7076. Min Act: -0.1700
Data Index: 6129649 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.7389. Min Act: -0.1700
Data Index: 281040 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.6764. Min Act: -0.1700
Data Index: 8416402 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.7076. Min Act: -0.1700
Data Index: 6324263 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.6451. Min Act: -0.1700
Data Index: 603974 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.6451. Min Act: -0.1700
Data Index: 1154868 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.6139. Min Act: -0.1700
Data Index: 3566589 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.5826. Min Act: -0.1700
Data Index: 3244822 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.5514. Min Act: -0.1700
Data Index: 7942163 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.5826. Min Act: -0.1700
Data Index: 1298615 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.5826. Min Act: -0.1700
Data Index: 8674642 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.5826. Min Act: -0.1700
Data Index: 5793933 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.5826. Min Act: -0.1700
Data Index: 163226 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.5826. Min Act: -0.1700
Data Index: 4659459 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.5201. Min Act: -0.1700
Data Index: 969192 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.5514. Min Act: -0.1700
Data Index: 7083143 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8014. Min Range: -4.8014
Max Act: 4.5201. Min Act: -0.1700
Data Index: 1080013 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19