Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6393 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1976. Min Range: -6.1976
Max Act: 6.1976. Min Act: -0.1700
Data Index: 8693727 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1976. Min Range: -6.1976
Max Act: 6.1351. Min Act: -0.1700
Data Index: 1297625 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1976. Min Range: -6.1976
Max Act: 6.0726. Min Act: -0.1700
Data Index: 3460898 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1976. Min Range: -6.1976
Max Act: 6.0414. Min Act: -0.1700
Data Index: 6204318 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1976. Min Range: -6.1976
Max Act: 6.0101. Min Act: -0.1700
Data Index: 617344 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.9789. Min Act: -0.1700
Data Index: 5888174 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.9789. Min Act: -0.1700
Data Index: 6583352 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.9164. Min Act: -0.1700
Data Index: 6153611 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.9476. Min Act: -0.1700
Data Index: 5401918 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.8851. Min Act: -0.1700
Data Index: 3372195 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.8539. Min Act: -0.1700
Data Index: 8009571 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.8851. Min Act: -0.1700
Data Index: 6841989 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.8539. Min Act: -0.1700
Data Index: 2101385 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.8539. Min Act: -0.1700
Data Index: 7399243 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.8226. Min Act: -0.1700
Data Index: 530890 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.8539. Min Act: -0.1700
Data Index: 420738 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.8539. Min Act: -0.1700
Data Index: 8777245 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.8226. Min Act: -0.1700
Data Index: 6422596 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.8226. Min Act: -0.1700
Data Index: 5507274 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1976. Min Range: -6.1976
Max Act: 5.8226. Min Act: -0.1700
Data Index: 2125530 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19