Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 497 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2951. Min Range: -6.2951
Max Act: 6.2951. Min Act: -0.1700
Data Index: 1402065 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2951. Min Range: -6.2951
Max Act: 6.2326. Min Act: -0.1700
Data Index: 3909639 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2951. Min Range: -6.2951
Max Act: 6.1701. Min Act: -0.1700
Data Index: 2087183 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2951. Min Range: -6.2951
Max Act: 6.0764. Min Act: -0.1700
Data Index: 492742 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2951. Min Range: -6.2951
Max Act: 6.1389. Min Act: -0.1700
Data Index: 7245073 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2951. Min Range: -6.2951
Max Act: 6.1076. Min Act: -0.1700
Data Index: 369715 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2951. Min Range: -6.2951
Max Act: 6.0764. Min Act: -0.1700
Data Index: 5250661 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2951. Min Range: -6.2951
Max Act: 6.0451. Min Act: -0.1700
Data Index: 6002373 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.9514. Min Act: -0.1700
Data Index: 8505039 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2951. Min Range: -6.2951
Max Act: 6.0139. Min Act: -0.1700
Data Index: 1108970 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.9826. Min Act: -0.1700
Data Index: 2101756 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.9826. Min Act: -0.1700
Data Index: 7406529 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.9826. Min Act: -0.1700
Data Index: 7248423 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.9826. Min Act: -0.1700
Data Index: 4463163 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.9826. Min Act: -0.1700
Data Index: 5785324 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.9826. Min Act: -0.1700
Data Index: 5514594 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.9201. Min Act: -0.1700
Data Index: 7355450 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.9514. Min Act: -0.1700
Data Index: 4548602 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.9201. Min Act: -0.1700
Data Index: 248425 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2951. Min Range: -6.2951
Max Act: 5.8889. Min Act: -0.1700
Data Index: 2121461 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19