Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3957 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.8512. Min Act: -0.1700
Data Index: 6552900 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.7887. Min Act: -0.1700
Data Index: 2965219 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.7262. Min Act: -0.1700
Data Index: 2013242 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.6637. Min Act: -0.1700
Data Index: 7023051 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.6012. Min Act: -0.1700
Data Index: 5539689 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.5700. Min Act: -0.1700
Data Index: 3702319 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.6012. Min Act: -0.1700
Data Index: 1121291 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.5700. Min Act: -0.1700
Data Index: 7190455 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.5700. Min Act: -0.1700
Data Index: 4682601 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.5075. Min Act: -0.1700
Data Index: 5299005 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.5075. Min Act: -0.1700
Data Index: 3137674 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.5075. Min Act: -0.1700
Data Index: 5169122 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.5075. Min Act: -0.1700
Data Index: 5134425 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.5075. Min Act: -0.1700
Data Index: 7472073 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.4762. Min Act: -0.1700
Data Index: 766035 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.4762. Min Act: -0.1700
Data Index: 8702976 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.4450. Min Act: -0.1700
Data Index: 629735 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.4762. Min Act: -0.1700
Data Index: 3640323 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.4450. Min Act: -0.1700
Data Index: 3012779 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8512. Min Range: -4.8512
Max Act: 4.4137. Min Act: -0.1700
Data Index: 6768864 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19