Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2779 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4071. Min Range: -6.4071
Max Act: 6.4071. Min Act: -0.1700
Data Index: 3399375 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4071. Min Range: -6.4071
Max Act: 6.2509. Min Act: -0.1700
Data Index: 3003620 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4071. Min Range: -6.4071
Max Act: 6.2196. Min Act: -0.1700
Data Index: 70022 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4071. Min Range: -6.4071
Max Act: 6.1884. Min Act: -0.1700
Data Index: 8500858 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4071. Min Range: -6.4071
Max Act: 6.1259. Min Act: -0.1700
Data Index: 6503574 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4071. Min Range: -6.4071
Max Act: 6.0946. Min Act: -0.1700
Data Index: 6084109 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4071. Min Range: -6.4071
Max Act: 6.0946. Min Act: -0.1700
Data Index: 4867560 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4071. Min Range: -6.4071
Max Act: 6.0321. Min Act: -0.1700
Data Index: 2890816 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4071. Min Range: -6.4071
Max Act: 5.9696. Min Act: -0.1700
Data Index: 1385759 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4071. Min Range: -6.4071
Max Act: 5.9696. Min Act: -0.1700
Data Index: 1553407 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4071. Min Range: -6.4071
Max Act: 5.9696. Min Act: -0.1700
Data Index: 8022647 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4071. Min Range: -6.4071
Max Act: 5.9696. Min Act: -0.1700
Data Index: 3988331 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4071. Min Range: -6.4071
Max Act: 5.9384. Min Act: -0.1700
Data Index: 6745401 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4071. Min Range: -6.4071
Max Act: 5.9384. Min Act: -0.1700
Data Index: 3066926 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4071. Min Range: -6.4071
Max Act: 5.9384. Min Act: -0.1700
Data Index: 798587 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4071. Min Range: -6.4071
Max Act: 5.9384. Min Act: -0.1700
Data Index: 1602855 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4071. Min Range: -6.4071
Max Act: 5.9071. Min Act: -0.1700
Data Index: 5345738 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4071. Min Range: -6.4071
Max Act: 5.9071. Min Act: -0.1700
Data Index: 1520782 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4071. Min Range: -6.4071
Max Act: 5.9071. Min Act: -0.1700
Data Index: 6381954 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4071. Min Range: -6.4071
Max Act: 5.9071. Min Act: -0.1700
Data Index: 1592475 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19