Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2441 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6949. Min Range: -8.6949
Max Act: 8.6949. Min Act: -0.1700
Data Index: 7047367 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.9136. Min Act: -0.1700
Data Index: 5224415 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.8824. Min Act: -0.1700
Data Index: 6747220 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.7574. Min Act: -0.1700
Data Index: 3738687 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.7574. Min Act: -0.1700
Data Index: 6189658 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.7261. Min Act: -0.1700
Data Index: 6418385 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.7261. Min Act: -0.1700
Data Index: 494109 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.6949. Min Act: -0.1700
Data Index: 6993075 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.7261. Min Act: -0.1700
Data Index: 379024 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.6011. Min Act: -0.1700
Data Index: 2987228 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.5699. Min Act: -0.1700
Data Index: 5922669 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.5699. Min Act: -0.1700
Data Index: 3803648 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.5386. Min Act: -0.1700
Data Index: 6384890 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.5074. Min Act: -0.1700
Data Index: 5582200 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.5074. Min Act: -0.1700
Data Index: 8591972 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.5074. Min Act: -0.1700
Data Index: 3467065 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.4449. Min Act: -0.1700
Data Index: 6481100 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.4136. Min Act: -0.1700
Data Index: 971866 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.4449. Min Act: -0.1700
Data Index: 8126757 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6949. Min Range: -8.6949
Max Act: 7.3824. Min Act: -0.1700
Data Index: 5792235 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19