Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 18 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0028. Min Range: -7.0028
Max Act: 7.0028. Min Act: -0.1700
Data Index: 2781654 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.9090. Min Act: -0.1700
Data Index: 8514928 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.7840. Min Act: -0.1700
Data Index: 1118173 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.6903. Min Act: -0.1700
Data Index: 4265136 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.6590. Min Act: -0.1700
Data Index: 6591707 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.6278. Min Act: -0.1700
Data Index: 1024124 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.5965. Min Act: -0.1700
Data Index: 5570122 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.6278. Min Act: -0.1700
Data Index: 8644816 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.6278. Min Act: -0.1700
Data Index: 8348189 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.5965. Min Act: -0.1700
Data Index: 2386866 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.6278. Min Act: -0.1700
Data Index: 3930339 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.6278. Min Act: -0.1700
Data Index: 8524927 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.5653. Min Act: -0.1700
Data Index: 4888521 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.5028. Min Act: -0.1700
Data Index: 4658156 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.5028. Min Act: -0.1700
Data Index: 2120024 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.5028. Min Act: -0.1700
Data Index: 791401 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.4715. Min Act: -0.1700
Data Index: 3521114 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.4715. Min Act: -0.1700
Data Index: 3231742 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.4715. Min Act: -0.1700
Data Index: 6194571 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0028. Min Range: -7.0028
Max Act: 6.4403. Min Act: -0.1700
Data Index: 8509528 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19