Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 54 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1343. Min Range: -2.1343
Max Act: 2.1343. Min Act: -0.1700
Data Index: 5636939 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1343. Min Range: -2.1343
Max Act: 2.1176. Min Act: -0.1700
Data Index: 5225886 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1343. Min Range: -2.1343
Max Act: 2.0841. Min Act: -0.1700
Data Index: 5125009 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1343. Min Range: -2.1343
Max Act: 2.0673. Min Act: -0.1700
Data Index: 6153719 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1343. Min Range: -2.1343
Max Act: 2.0168. Min Act: -0.1700
Data Index: 8280807 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1343. Min Range: -2.1343
Max Act: 2.0337. Min Act: -0.1700
Data Index: 5816590 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1343. Min Range: -2.1343
Max Act: 2.0337. Min Act: -0.1700
Data Index: 5409813 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1343. Min Range: -2.1343
Max Act: 2.0168. Min Act: -0.1700
Data Index: 290708 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1343. Min Range: -2.1343
Max Act: 2.0168. Min Act: -0.1700
Data Index: 6098454 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1343. Min Range: -2.1343
Max Act: 1.9999. Min Act: -0.1700
Data Index: 8299549 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1343. Min Range: -2.1343
Max Act: 1.9830. Min Act: -0.1700
Data Index: 7707094 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1343. Min Range: -2.1343
Max Act: 1.9999. Min Act: -0.1700
Data Index: 745564 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1343. Min Range: -2.1343
Max Act: 1.9491. Min Act: -0.1700
Data Index: 5012272 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1343. Min Range: -2.1343
Max Act: 1.9661. Min Act: -0.1700
Data Index: 5199431 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1343. Min Range: -2.1343
Max Act: 1.9661. Min Act: -0.1700
Data Index: 1300843 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1343. Min Range: -2.1343
Max Act: 1.9661. Min Act: -0.1700
Data Index: 6330822 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1343. Min Range: -2.1343
Max Act: 1.9661. Min Act: -0.1700
Data Index: 7685595 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1343. Min Range: -2.1343
Max Act: 1.9661. Min Act: -0.1700
Data Index: 2059651 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1343. Min Range: -2.1343
Max Act: 1.9661. Min Act: -0.1700
Data Index: 1523848 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1343. Min Range: -2.1343
Max Act: 1.9491. Min Act: -0.1700
Data Index: 7665104 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19