Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 678 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1123. Min Range: -6.1123
Max Act: 6.1123. Min Act: -0.1700
Data Index: 8150114 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1123. Min Range: -6.1123
Max Act: 6.0811. Min Act: -0.1700
Data Index: 8755837 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1123. Min Range: -6.1123
Max Act: 6.0498. Min Act: -0.1700
Data Index: 2749928 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1123. Min Range: -6.1123
Max Act: 6.0186. Min Act: -0.1700
Data Index: 1563974 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1123. Min Range: -6.1123
Max Act: 6.0186. Min Act: -0.1700
Data Index: 5435144 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1123. Min Range: -6.1123
Max Act: 6.0186. Min Act: -0.1700
Data Index: 4152084 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1123. Min Range: -6.1123
Max Act: 5.9561. Min Act: -0.1700
Data Index: 6062416 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1123. Min Range: -6.1123
Max Act: 5.9561. Min Act: -0.1700
Data Index: 6088487 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1123. Min Range: -6.1123
Max Act: 5.9561. Min Act: -0.1700
Data Index: 483447 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1123. Min Range: -6.1123
Max Act: 5.9248. Min Act: -0.1700
Data Index: 3741116 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1123. Min Range: -6.1123
Max Act: 5.9248. Min Act: -0.1700
Data Index: 3169779 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1123. Min Range: -6.1123
Max Act: 5.9248. Min Act: -0.1700
Data Index: 34229 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1123. Min Range: -6.1123
Max Act: 5.8936. Min Act: -0.1700
Data Index: 4411741 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1123. Min Range: -6.1123
Max Act: 5.8936. Min Act: -0.1700
Data Index: 8475825 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1123. Min Range: -6.1123
Max Act: 5.8936. Min Act: -0.1700
Data Index: 1948396 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1123. Min Range: -6.1123
Max Act: 5.8936. Min Act: -0.1700
Data Index: 8024979 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1123. Min Range: -6.1123
Max Act: 5.8623. Min Act: -0.1700
Data Index: 6355745 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1123. Min Range: -6.1123
Max Act: 5.8623. Min Act: -0.1700
Data Index: 8539229 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1123. Min Range: -6.1123
Max Act: 5.8311. Min Act: -0.1700
Data Index: 7139380 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1123. Min Range: -6.1123
Max Act: 5.8311. Min Act: -0.1700
Data Index: 1021676 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19