Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3356 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.5758. Min Act: -0.1700
Data Index: 785554 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.5133. Min Act: -0.1700
Data Index: 1974891 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.4195. Min Act: -0.1700
Data Index: 7039607 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.3883. Min Act: -0.1700
Data Index: 757472 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.4195. Min Act: -0.1700
Data Index: 2999781 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.3570. Min Act: -0.1700
Data Index: 6494600 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.3570. Min Act: -0.1700
Data Index: 4055500 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.3258. Min Act: -0.1700
Data Index: 6238813 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.2945. Min Act: -0.1700
Data Index: 7158831 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.2945. Min Act: -0.1700
Data Index: 5083570 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.2945. Min Act: -0.1700
Data Index: 7293787 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.2945. Min Act: -0.1700
Data Index: 3818614 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.2633. Min Act: -0.1700
Data Index: 5741045 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.2633. Min Act: -0.1700
Data Index: 2957898 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.2633. Min Act: -0.1700
Data Index: 245598 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.2320. Min Act: -0.1700
Data Index: 3321685 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.2320. Min Act: -0.1700
Data Index: 6097518 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.2320. Min Act: -0.1700
Data Index: 7480587 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.2320. Min Act: -0.1700
Data Index: 3192189 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5758. Min Range: -4.5758
Max Act: 4.2008. Min Act: -0.1700
Data Index: 3042835 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19