Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1135 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0762. Min Range: -6.0762
Max Act: 6.0762. Min Act: -0.1700
Data Index: 949384 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.9512. Min Act: -0.1700
Data Index: 1912450 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.8887. Min Act: -0.1700
Data Index: 1428858 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.8575. Min Act: -0.1700
Data Index: 3926205 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.7950. Min Act: -0.1700
Data Index: 879786 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.8262. Min Act: -0.1700
Data Index: 1526556 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.7637. Min Act: -0.1700
Data Index: 3606485 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.7325. Min Act: -0.1700
Data Index: 2980902 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.7012. Min Act: -0.1700
Data Index: 4921742 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.7012. Min Act: -0.1700
Data Index: 2715062 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.7012. Min Act: -0.1700
Data Index: 3092128 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.7012. Min Act: -0.1700
Data Index: 8757800 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.6700. Min Act: -0.1700
Data Index: 957449 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.6700. Min Act: -0.1700
Data Index: 8617120 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.6700. Min Act: -0.1700
Data Index: 4040724 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.6387. Min Act: -0.1700
Data Index: 2698063 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.6387. Min Act: -0.1700
Data Index: 7975508 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.6075. Min Act: -0.1700
Data Index: 252402 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.5762. Min Act: -0.1700
Data Index: 4718773 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0762. Min Range: -6.0762
Max Act: 5.5762. Min Act: -0.1700
Data Index: 311378 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19