Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2742 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 19.7148. Min Range: -19.7148
Max Act: 19.7148. Min Act: -0.1700
Data Index: 7343784 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 19.7148. Min Range: -19.7148
Max Act: 18.4648. Min Act: -0.1700
Data Index: 3984799 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 19.7148. Min Range: -19.7148
Max Act: 18.5898. Min Act: -0.1700
Data Index: 4043581 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 19.7148. Min Range: -19.7148
Max Act: 18.3398. Min Act: -0.1700
Data Index: 947835 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 19.7148. Min Range: -19.7148
Max Act: 18.3398. Min Act: -0.1700
Data Index: 3868157 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 19.7148. Min Range: -19.7148
Max Act: 18.2148. Min Act: -0.1698
Data Index: 4250764 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 19.7148. Min Range: -19.7148
Max Act: 17.9648. Min Act: -0.1700
Data Index: 8450056 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 19.7148. Min Range: -19.7148
Max Act: 18.0898. Min Act: -0.1700
Data Index: 4365371 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 19.7148. Min Range: -19.7148
Max Act: 17.9648. Min Act: -0.1700
Data Index: 5310983 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 19.7148. Min Range: -19.7148
Max Act: 18.0898. Min Act: -0.1700
Data Index: 7852569 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 19.7148. Min Range: -19.7148
Max Act: 17.9648. Min Act: -0.1700
Data Index: 8786008 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 19.7148. Min Range: -19.7148
Max Act: 17.9648. Min Act: -0.1700
Data Index: 8786006 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 19.7148. Min Range: -19.7148
Max Act: 17.9648. Min Act: -0.1700
Data Index: 2783620 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 19.7148. Min Range: -19.7148
Max Act: 17.9648. Min Act: -0.1700
Data Index: 7852594 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 19.7148. Min Range: -19.7148
Max Act: 17.9648. Min Act: -0.1700
Data Index: 1020954 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 19.7148. Min Range: -19.7148
Max Act: 17.8398. Min Act: -0.1700
Data Index: 8786007 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 19.7148. Min Range: -19.7148
Max Act: 17.7148. Min Act: -0.1700
Data Index: 8777660 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 19.7148. Min Range: -19.7148
Max Act: 17.7148. Min Act: -0.1699
Data Index: 5724509 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 19.7148. Min Range: -19.7148
Max Act: 17.5898. Min Act: -0.1700
Data Index: 1020937 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 19.7148. Min Range: -19.7148
Max Act: 17.7148. Min Act: -0.1700
Data Index: 1537917 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19