Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1931 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.9417. Min Act: -0.1700
Data Index: 8156085 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.8479. Min Act: -0.1700
Data Index: 3303094 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.8479. Min Act: -0.1700
Data Index: 3451025 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.8167. Min Act: -0.1700
Data Index: 1955993 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.7854. Min Act: -0.1700
Data Index: 6056088 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.7229. Min Act: -0.1700
Data Index: 5138800 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.7229. Min Act: -0.1700
Data Index: 5710537 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.6917. Min Act: -0.1700
Data Index: 6280625 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.6917. Min Act: -0.1700
Data Index: 2076147 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.6604. Min Act: -0.1700
Data Index: 3382607 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.6604. Min Act: -0.1700
Data Index: 5933763 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.6604. Min Act: -0.1700
Data Index: 6744448 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.6604. Min Act: -0.1700
Data Index: 7572121 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.6604. Min Act: -0.1700
Data Index: 1749745 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.6292. Min Act: -0.1700
Data Index: 6963762 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.5979. Min Act: -0.1700
Data Index: 1354975 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.5979. Min Act: -0.1700
Data Index: 8671391 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.5667. Min Act: -0.1700
Data Index: 2681175 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.5979. Min Act: -0.1700
Data Index: 7912077 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9417. Min Range: -6.9417
Max Act: 6.5667. Min Act: -0.1700
Data Index: 4504971 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19