Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2098 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2093. Min Range: -6.2093
Max Act: 6.2093. Min Act: -0.1700
Data Index: 3893621 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2093. Min Range: -6.2093
Max Act: 6.0218. Min Act: -0.1700
Data Index: 2448080 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.9593. Min Act: -0.1700
Data Index: 7081487 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.9593. Min Act: -0.1700
Data Index: 723836 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.8968. Min Act: -0.1700
Data Index: 7284658 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.8655. Min Act: -0.1700
Data Index: 5366079 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.8343. Min Act: -0.1700
Data Index: 4577060 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.8343. Min Act: -0.1700
Data Index: 2537908 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.8343. Min Act: -0.1700
Data Index: 5262680 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.8343. Min Act: -0.1700
Data Index: 6764423 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.8343. Min Act: -0.1700
Data Index: 3797141 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.7718. Min Act: -0.1700
Data Index: 6999173 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.8030. Min Act: -0.1700
Data Index: 5037008 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.7718. Min Act: -0.1700
Data Index: 2858932 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.7718. Min Act: -0.1700
Data Index: 1013191 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.7405. Min Act: -0.1700
Data Index: 1258367 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.7718. Min Act: -0.1700
Data Index: 7346008 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.7405. Min Act: -0.1700
Data Index: 277294 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.7405. Min Act: -0.1700
Data Index: 867052 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2093. Min Range: -6.2093
Max Act: 5.7405. Min Act: -0.1700
Data Index: 5793571 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19