Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5089 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1977. Min Range: -9.1977
Max Act: 9.1977. Min Act: -0.1700
Data Index: 5066596 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1977. Min Range: -9.1977
Max Act: 9.0102. Min Act: -0.1700
Data Index: 4895667 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1977. Min Range: -9.1977
Max Act: 9.0102. Min Act: -0.1700
Data Index: 7095173 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1977. Min Range: -9.1977
Max Act: 8.8852. Min Act: -0.1700
Data Index: 8361449 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1977. Min Range: -9.1977
Max Act: 8.8227. Min Act: -0.1700
Data Index: 7588153 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1977. Min Range: -9.1977
Max Act: 8.7602. Min Act: -0.1700
Data Index: 1419113 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1977. Min Range: -9.1977
Max Act: 8.7602. Min Act: -0.1700
Data Index: 4952908 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1977. Min Range: -9.1977
Max Act: 8.6977. Min Act: -0.1700
Data Index: 5230481 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1977. Min Range: -9.1977
Max Act: 8.6977. Min Act: -0.1700
Data Index: 7061830 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1977. Min Range: -9.1977
Max Act: 8.6352. Min Act: -0.1700
Data Index: 4656494 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1977. Min Range: -9.1977
Max Act: 8.6352. Min Act: -0.1700
Data Index: 86126 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1977. Min Range: -9.1977
Max Act: 8.5727. Min Act: -0.1700
Data Index: 4707246 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1977. Min Range: -9.1977
Max Act: 8.5727. Min Act: -0.1700
Data Index: 3343815 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1977. Min Range: -9.1977
Max Act: 8.5727. Min Act: -0.1700
Data Index: 1483600 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1977. Min Range: -9.1977
Max Act: 8.5102. Min Act: -0.1700
Data Index: 7581731 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1977. Min Range: -9.1977
Max Act: 8.5102. Min Act: -0.1700
Data Index: 8513008 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1977. Min Range: -9.1977
Max Act: 8.5102. Min Act: -0.1700
Data Index: 3619045 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1977. Min Range: -9.1977
Max Act: 8.5102. Min Act: -0.1700
Data Index: 5693518 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1977. Min Range: -9.1977
Max Act: 8.4477. Min Act: -0.1700
Data Index: 3730662 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1977. Min Range: -9.1977
Max Act: 8.4477. Min Act: -0.1700
Data Index: 5052792 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19