Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 497 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.5244. Min Act: -0.1700
Data Index: 1880041 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.4619. Min Act: -0.1700
Data Index: 5211629 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.4932. Min Act: -0.1700
Data Index: 7196769 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.4307. Min Act: -0.1700
Data Index: 6202401 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.3994. Min Act: -0.1700
Data Index: 683070 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.4307. Min Act: -0.1700
Data Index: 6202397 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.4307. Min Act: -0.1700
Data Index: 1289813 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.3994. Min Act: -0.1700
Data Index: 6135701 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.3994. Min Act: -0.1700
Data Index: 3850513 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.3369. Min Act: -0.1700
Data Index: 2753782 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.3057. Min Act: -0.1700
Data Index: 7390515 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.3057. Min Act: -0.1700
Data Index: 658610 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.3682. Min Act: -0.1700
Data Index: 8752134 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.3682. Min Act: -0.1700
Data Index: 453633 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.2744. Min Act: -0.1700
Data Index: 444692 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.3369. Min Act: -0.1700
Data Index: 2561083 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.2744. Min Act: -0.1700
Data Index: 39895 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.3369. Min Act: -0.1700
Data Index: 1273338 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.3057. Min Act: -0.1700
Data Index: 4087434 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5244. Min Range: -6.5244
Max Act: 6.2744. Min Act: -0.1700
Data Index: 3886278 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19