Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2319 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4035. Min Range: -7.4035
Max Act: 7.3722. Min Act: -0.1700
Data Index: 8344938 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4035. Min Range: -7.4035
Max Act: 7.4035. Min Act: -0.1700
Data Index: 39244 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4035. Min Range: -7.4035
Max Act: 7.2472. Min Act: -0.1700
Data Index: 761019 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4035. Min Range: -7.4035
Max Act: 7.1847. Min Act: -0.1700
Data Index: 7340251 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4035. Min Range: -7.4035
Max Act: 7.1535. Min Act: -0.1700
Data Index: 604508 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4035. Min Range: -7.4035
Max Act: 7.1222. Min Act: -0.1700
Data Index: 1976609 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4035. Min Range: -7.4035
Max Act: 7.0597. Min Act: -0.1700
Data Index: 2211817 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4035. Min Range: -7.4035
Max Act: 6.9660. Min Act: -0.1700
Data Index: 1876107 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4035. Min Range: -7.4035
Max Act: 6.9660. Min Act: -0.1700
Data Index: 2556248 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4035. Min Range: -7.4035
Max Act: 6.9660. Min Act: -0.1700
Data Index: 3751978 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4035. Min Range: -7.4035
Max Act: 6.9035. Min Act: -0.1700
Data Index: 8167757 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4035. Min Range: -7.4035
Max Act: 6.8722. Min Act: -0.1700
Data Index: 606438 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4035. Min Range: -7.4035
Max Act: 6.9035. Min Act: -0.1700
Data Index: 4613102 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4035. Min Range: -7.4035
Max Act: 6.9035. Min Act: -0.1700
Data Index: 2160346 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4035. Min Range: -7.4035
Max Act: 6.8722. Min Act: -0.1700
Data Index: 5643474 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4035. Min Range: -7.4035
Max Act: 6.8722. Min Act: -0.1700
Data Index: 5644860 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4035. Min Range: -7.4035
Max Act: 6.8722. Min Act: -0.1700
Data Index: 70547 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4035. Min Range: -7.4035
Max Act: 6.8410. Min Act: -0.1700
Data Index: 6088492 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4035. Min Range: -7.4035
Max Act: 6.8410. Min Act: -0.1700
Data Index: 5391429 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4035. Min Range: -7.4035
Max Act: 6.8410. Min Act: -0.1700
Data Index: 4984893 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19