Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4165 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.9907. Min Act: -0.1700
Data Index: 2793400 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.9594. Min Act: -0.1700
Data Index: 1666727 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.8969. Min Act: -0.1700
Data Index: 7852360 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.8344. Min Act: -0.1700
Data Index: 7309720 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.8344. Min Act: -0.1700
Data Index: 8056299 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.8032. Min Act: -0.1700
Data Index: 1644071 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.7719. Min Act: -0.1700
Data Index: 5567628 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.7719. Min Act: -0.1700
Data Index: 5013773 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.7719. Min Act: -0.1700
Data Index: 2711640 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.8032. Min Act: -0.1700
Data Index: 7238906 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.7719. Min Act: -0.1700
Data Index: 6567317 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.7407. Min Act: -0.1700
Data Index: 8030347 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.7407. Min Act: -0.1700
Data Index: 5329343 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.7094. Min Act: -0.1700
Data Index: 2032956 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.7094. Min Act: -0.1700
Data Index: 4659451 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.6782. Min Act: -0.1700
Data Index: 1161226 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.6782. Min Act: -0.1700
Data Index: 7633899 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.6782. Min Act: -0.1700
Data Index: 4080680 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.6782. Min Act: -0.1700
Data Index: 943485 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9907. Min Range: -5.9907
Max Act: 5.6782. Min Act: -0.1700
Data Index: 501120 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19