Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 918 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5494. Min Range: -5.5494
Max Act: 5.5494. Min Act: -0.1700
Data Index: 8256559 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5494. Min Range: -5.5494
Max Act: 5.5182. Min Act: -0.1700
Data Index: 6050092 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5494. Min Range: -5.5494
Max Act: 5.2682. Min Act: -0.1700
Data Index: 6141997 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5494. Min Range: -5.5494
Max Act: 5.2369. Min Act: -0.1700
Data Index: 5882282 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5494. Min Range: -5.5494
Max Act: 5.2057. Min Act: -0.1700
Data Index: 1482915 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5494. Min Range: -5.5494
Max Act: 5.2057. Min Act: -0.1700
Data Index: 610397 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5494. Min Range: -5.5494
Max Act: 5.1744. Min Act: -0.1700
Data Index: 1870217 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5494. Min Range: -5.5494
Max Act: 5.1744. Min Act: -0.1700
Data Index: 5438448 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5494. Min Range: -5.5494
Max Act: 5.1432. Min Act: -0.1700
Data Index: 1395182 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5494. Min Range: -5.5494
Max Act: 5.1119. Min Act: -0.1700
Data Index: 1654061 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5494. Min Range: -5.5494
Max Act: 5.1432. Min Act: -0.1700
Data Index: 8554016 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5494. Min Range: -5.5494
Max Act: 5.0807. Min Act: -0.1700
Data Index: 8742200 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5494. Min Range: -5.5494
Max Act: 5.0807. Min Act: -0.1700
Data Index: 2976804 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5494. Min Range: -5.5494
Max Act: 5.0182. Min Act: -0.1700
Data Index: 2574739 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5494. Min Range: -5.5494
Max Act: 5.0494. Min Act: -0.1700
Data Index: 6584369 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5494. Min Range: -5.5494
Max Act: 5.0182. Min Act: -0.1700
Data Index: 5758159 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5494. Min Range: -5.5494
Max Act: 5.0182. Min Act: -0.1700
Data Index: 8626131 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5494. Min Range: -5.5494
Max Act: 4.9869. Min Act: -0.1700
Data Index: 3550908 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5494. Min Range: -5.5494
Max Act: 4.9869. Min Act: -0.1700
Data Index: 3968701 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5494. Min Range: -5.5494
Max Act: 4.9869. Min Act: -0.1700
Data Index: 8492775 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19