Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1117 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.6689. Min Act: -0.1700
Data Index: 1857526 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.6376. Min Act: -0.1700
Data Index: 7409039 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.6063. Min Act: -0.1700
Data Index: 2801146 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.6063. Min Act: -0.1700
Data Index: 2966014 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.5907. Min Act: -0.1700
Data Index: 567076 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.5593. Min Act: -0.1700
Data Index: 3316967 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.5593. Min Act: -0.1700
Data Index: 7839101 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.5437. Min Act: -0.1700
Data Index: 7242679 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.5593. Min Act: -0.1700
Data Index: 5906614 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.5124. Min Act: -0.1700
Data Index: 1576460 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.5124. Min Act: -0.1700
Data Index: 4662077 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.5280. Min Act: -0.1700
Data Index: 5995402 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.4967. Min Act: -0.1700
Data Index: 7919268 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.4810. Min Act: -0.1700
Data Index: 398294 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.4654. Min Act: -0.1700
Data Index: 5736587 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.4654. Min Act: -0.1700
Data Index: 3933331 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.4654. Min Act: -0.1700
Data Index: 7592402 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.4497. Min Act: -0.1700
Data Index: 3303859 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.4340. Min Act: -0.1700
Data Index: 6989992 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6689. Min Range: -3.6689
Max Act: 3.4340. Min Act: -0.1700
Data Index: 5993929 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19