Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1884. Min Range: -9.1884
Max Act: 9.1884. Min Act: -0.1700
Data Index: 8363733 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.8759. Min Act: -0.1700
Data Index: 4464583 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.8134. Min Act: -0.1700
Data Index: 1076847 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.8759. Min Act: -0.1700
Data Index: 569984 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.8759. Min Act: -0.1700
Data Index: 839579 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.8134. Min Act: -0.1700
Data Index: 138917 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.6884. Min Act: -0.1700
Data Index: 1283743 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.6884. Min Act: -0.1700
Data Index: 593143 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.5634. Min Act: -0.1700
Data Index: 7340345 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.5634. Min Act: -0.1700
Data Index: 3312472 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.5634. Min Act: -0.1700
Data Index: 515638 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.5634. Min Act: -0.1700
Data Index: 1349486 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.5634. Min Act: -0.1700
Data Index: 3967753 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.5009. Min Act: -0.1700
Data Index: 223237 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.5009. Min Act: -0.1700
Data Index: 1036185 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.5634. Min Act: -0.1700
Data Index: 2044096 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.5634. Min Act: -0.1700
Data Index: 5042422 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.5009. Min Act: -0.1700
Data Index: 1325517 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.4384. Min Act: -0.1700
Data Index: 3388044 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1884. Min Range: -9.1884
Max Act: 8.4384. Min Act: -0.1700
Data Index: 5438450 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19