Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3621 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.9128. Min Act: -0.1700
Data Index: 6641589 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.6940. Min Act: -0.1700
Data Index: 1051406 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.5690. Min Act: -0.1700
Data Index: 394601 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.5378. Min Act: -0.1700
Data Index: 5198914 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.5065. Min Act: -0.1700
Data Index: 4423861 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.4753. Min Act: -0.1700
Data Index: 8067934 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.3190. Min Act: -0.1700
Data Index: 6795867 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.2565. Min Act: -0.1700
Data Index: 1608158 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.2253. Min Act: -0.1700
Data Index: 7855699 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.1940. Min Act: -0.1700
Data Index: 4783589 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.1940. Min Act: -0.1700
Data Index: 246301 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.1940. Min Act: -0.1700
Data Index: 858094 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.0690. Min Act: -0.1700
Data Index: 2025819 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.0690. Min Act: -0.1700
Data Index: 1827590 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.0690. Min Act: -0.1700
Data Index: 635661 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.0690. Min Act: -0.1700
Data Index: 393786 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.0378. Min Act: -0.1700
Data Index: 5572044 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.0690. Min Act: -0.1700
Data Index: 2736838 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9128. Min Range: -7.9128
Max Act: 7.0378. Min Act: -0.1700
Data Index: 4371345 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9128. Min Range: -7.9128
Max Act: 6.9753. Min Act: -0.1700
Data Index: 7804077 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19