Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2381 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.9875. Min Act: -0.1700
Data Index: 3069660 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.9562. Min Act: -0.1700
Data Index: 3505876 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.8937. Min Act: -0.1700
Data Index: 1040949 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.9250. Min Act: -0.1700
Data Index: 8411851 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.8625. Min Act: -0.1700
Data Index: 6295620 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.7687. Min Act: -0.1700
Data Index: 5188238 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.7687. Min Act: -0.1700
Data Index: 3699630 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.7062. Min Act: -0.1700
Data Index: 236290 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.7062. Min Act: -0.1700
Data Index: 7099614 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.6750. Min Act: -0.1700
Data Index: 218367 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.6750. Min Act: -0.1700
Data Index: 5694996 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.6750. Min Act: -0.1700
Data Index: 8516992 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.6437. Min Act: -0.1700
Data Index: 750506 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.6750. Min Act: -0.1700
Data Index: 4861017 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.6750. Min Act: -0.1700
Data Index: 8318667 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.6437. Min Act: -0.1700
Data Index: 8551879 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.6437. Min Act: -0.1700
Data Index: 7063778 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.6750. Min Act: -0.1700
Data Index: 4766749 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.6125. Min Act: -0.1700
Data Index: 6720142 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.5812. Min Act: -0.1700
Data Index: 1269132 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19