Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5018. Min Range: -8.5018
Max Act: 8.5018. Min Act: -0.1700
Data Index: 439938 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5018. Min Range: -8.5018
Max Act: 8.0643. Min Act: -0.1700
Data Index: 4891967 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5018. Min Range: -8.5018
Max Act: 8.0331. Min Act: -0.1700
Data Index: 402781 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5018. Min Range: -8.5018
Max Act: 7.8456. Min Act: -0.1700
Data Index: 3981937 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5018. Min Range: -8.5018
Max Act: 7.8456. Min Act: -0.1700
Data Index: 232744 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5018. Min Range: -8.5018
Max Act: 7.7831. Min Act: -0.1700
Data Index: 1059613 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5018. Min Range: -8.5018
Max Act: 7.6893. Min Act: -0.1700
Data Index: 4671123 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5018. Min Range: -8.5018
Max Act: 7.5956. Min Act: -0.1700
Data Index: 8143179 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5018. Min Range: -8.5018
Max Act: 7.6268. Min Act: -0.1700
Data Index: 1955119 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5018. Min Range: -8.5018
Max Act: 7.5643. Min Act: -0.1700
Data Index: 6523552 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5018. Min Range: -8.5018
Max Act: 7.5956. Min Act: -0.1700
Data Index: 980647 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5018. Min Range: -8.5018
Max Act: 7.5956. Min Act: -0.1700
Data Index: 6666140 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5018. Min Range: -8.5018
Max Act: 7.5643. Min Act: -0.1700
Data Index: 1689311 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5018. Min Range: -8.5018
Max Act: 7.5331. Min Act: -0.1700
Data Index: 1179894 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5018. Min Range: -8.5018
Max Act: 7.5018. Min Act: -0.1700
Data Index: 7688505 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5018. Min Range: -8.5018
Max Act: 7.5018. Min Act: -0.1700
Data Index: 3026505 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5018. Min Range: -8.5018
Max Act: 7.4706. Min Act: -0.1700
Data Index: 8757440 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5018. Min Range: -8.5018
Max Act: 7.4706. Min Act: -0.1700
Data Index: 2995131 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5018. Min Range: -8.5018
Max Act: 7.4393. Min Act: -0.1700
Data Index: 1458223 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5018. Min Range: -8.5018
Max Act: 7.4393. Min Act: -0.1700
Data Index: 4634088 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19