Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3607 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.8977. Min Act: -0.1700
Data Index: 5455587 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.8352. Min Act: -0.1700
Data Index: 3746275 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.7727. Min Act: -0.1700
Data Index: 4251524 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.7102. Min Act: -0.1700
Data Index: 2017438 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.7102. Min Act: -0.1700
Data Index: 1638117 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.7102. Min Act: -0.1700
Data Index: 5372715 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.6789. Min Act: -0.1700
Data Index: 6912121 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.6477. Min Act: -0.1700
Data Index: 5900380 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.6164. Min Act: -0.1700
Data Index: 6971800 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.6164. Min Act: -0.1700
Data Index: 3714173 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.5852. Min Act: -0.1700
Data Index: 1450631 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.5539. Min Act: -0.1700
Data Index: 7356601 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.5539. Min Act: -0.1700
Data Index: 3416699 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.5539. Min Act: -0.1700
Data Index: 6462374 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.5539. Min Act: -0.1700
Data Index: 2141028 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.4914. Min Act: -0.1700
Data Index: 8043562 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.5227. Min Act: -0.1700
Data Index: 1051806 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.4914. Min Act: -0.1700
Data Index: 800751 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.5227. Min Act: -0.1700
Data Index: 6155717 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8977. Min Range: -5.8977
Max Act: 5.4914. Min Act: -0.1700
Data Index: 53977 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19