Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3033 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.3604. Min Act: -0.1700
Data Index: 708279 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.3604. Min Act: -0.1700
Data Index: 7030544 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.2979. Min Act: -0.1700
Data Index: 1644221 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.2979. Min Act: -0.1700
Data Index: 875376 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.2354. Min Act: -0.1700
Data Index: 7374357 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.2667. Min Act: -0.1700
Data Index: 6505369 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.2354. Min Act: -0.1700
Data Index: 4895990 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.2042. Min Act: -0.1700
Data Index: 5087550 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.1729. Min Act: -0.1698
Data Index: 7918757 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.1729. Min Act: -0.1700
Data Index: 7049893 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.1729. Min Act: -0.1700
Data Index: 3714772 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.1729. Min Act: -0.1700
Data Index: 3237698 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.1417. Min Act: -0.1700
Data Index: 3334320 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.1417. Min Act: -0.1700
Data Index: 4323034 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.1417. Min Act: -0.1700
Data Index: 1758630 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.1417. Min Act: -0.1700
Data Index: 4536664 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.1417. Min Act: -0.1700
Data Index: 4861025 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.1417. Min Act: -0.1700
Data Index: 528608 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.1417. Min Act: -0.1700
Data Index: 115073 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3604. Min Range: -5.3604
Max Act: 5.1417. Min Act: -0.1700
Data Index: 1851575 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19