Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2161 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.9915. Min Act: -0.1700
Data Index: 5099570 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.9603. Min Act: -0.1700
Data Index: 2933869 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.8978. Min Act: -0.1700
Data Index: 2066560 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.8665. Min Act: -0.1700
Data Index: 3005903 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.8665. Min Act: -0.1700
Data Index: 3931933 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.8040. Min Act: -0.1700
Data Index: 1957067 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.8040. Min Act: -0.1700
Data Index: 1448285 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.7415. Min Act: -0.1700
Data Index: 6775082 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.7728. Min Act: -0.1700
Data Index: 4627069 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.7415. Min Act: -0.1700
Data Index: 6775079 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.7415. Min Act: -0.1700
Data Index: 1025526 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.7415. Min Act: -0.1700
Data Index: 2269044 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.7103. Min Act: -0.1700
Data Index: 51047 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.7103. Min Act: -0.1700
Data Index: 5079515 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.6790. Min Act: -0.1700
Data Index: 1542858 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.6478. Min Act: -0.1700
Data Index: 8320568 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.6165. Min Act: -0.1700
Data Index: 210761 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.6165. Min Act: -0.1700
Data Index: 5116264 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.6165. Min Act: -0.1700
Data Index: 3165187 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9915. Min Range: -6.9915
Max Act: 6.5540. Min Act: -0.1700
Data Index: 6829753 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19