Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4417 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6095. Min Range: -7.6095
Max Act: 7.6095. Min Act: -0.1700
Data Index: 4962427 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6095. Min Range: -7.6095
Max Act: 7.4845. Min Act: -0.1700
Data Index: 5775542 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6095. Min Range: -7.6095
Max Act: 7.3595. Min Act: -0.1700
Data Index: 474021 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6095. Min Range: -7.6095
Max Act: 7.3283. Min Act: -0.1700
Data Index: 8465370 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6095. Min Range: -7.6095
Max Act: 7.2033. Min Act: -0.1700
Data Index: 5271463 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6095. Min Range: -7.6095
Max Act: 7.1720. Min Act: -0.1700
Data Index: 944210 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6095. Min Range: -7.6095
Max Act: 7.1408. Min Act: -0.1700
Data Index: 5994363 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6095. Min Range: -7.6095
Max Act: 7.0783. Min Act: -0.1700
Data Index: 1035600 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6095. Min Range: -7.6095
Max Act: 7.1408. Min Act: -0.1700
Data Index: 6817297 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6095. Min Range: -7.6095
Max Act: 7.0783. Min Act: -0.1700
Data Index: 7882270 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6095. Min Range: -7.6095
Max Act: 7.0470. Min Act: -0.1700
Data Index: 3243265 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6095. Min Range: -7.6095
Max Act: 7.0158. Min Act: -0.1700
Data Index: 1108521 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.9533. Min Act: -0.1700
Data Index: 3105851 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.9533. Min Act: -0.1700
Data Index: 3319830 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.9220. Min Act: -0.1700
Data Index: 2063797 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.9220. Min Act: -0.1700
Data Index: 2840482 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.9220. Min Act: -0.1700
Data Index: 3296932 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.8595. Min Act: -0.1700
Data Index: 7927167 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.8908. Min Act: -0.1700
Data Index: 1172627 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.8908. Min Act: -0.1700
Data Index: 1968431 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19