Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3608 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.4164. Min Act: -0.1700
Data Index: 2158927 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.3539. Min Act: -0.1700
Data Index: 1359455 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.2914. Min Act: -0.1700
Data Index: 7727722 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.2914. Min Act: -0.1700
Data Index: 7002910 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.2914. Min Act: -0.1700
Data Index: 485640 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.2602. Min Act: -0.1700
Data Index: 856439 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.1664. Min Act: -0.1700
Data Index: 74535 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.1664. Min Act: -0.1700
Data Index: 4108199 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.1664. Min Act: -0.1700
Data Index: 8637575 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.1352. Min Act: -0.1700
Data Index: 4100251 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.1039. Min Act: -0.1700
Data Index: 3198018 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.1039. Min Act: -0.1700
Data Index: 6057122 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.0727. Min Act: -0.1700
Data Index: 2431604 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.0727. Min Act: -0.1700
Data Index: 2730730 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.0727. Min Act: -0.1700
Data Index: 7321186 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.0727. Min Act: -0.1700
Data Index: 6054092 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.0727. Min Act: -0.1700
Data Index: 5547211 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.0414. Min Act: -0.1700
Data Index: 6093714 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.0727. Min Act: -0.1700
Data Index: 6158590 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4164. Min Range: -6.4164
Max Act: 6.0727. Min Act: -0.1700
Data Index: 6107767 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19