Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5985 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.2434. Min Act: -0.1700
Data Index: 5556055 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.1104. Min Act: -0.1699
Data Index: 7334148 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.1104. Min Act: -0.1681
Data Index: 6574606 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.1104. Min Act: -0.1700
Data Index: 4457881 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.1104. Min Act: -0.1697
Data Index: 2741631 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.0936. Min Act: -0.1658
Data Index: 159723 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.0769. Min Act: -0.1699
Data Index: 5556058 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.0936. Min Act: -0.1700
Data Index: 8460338 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.0601. Min Act: -0.1700
Data Index: 4928842 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.0769. Min Act: -0.1694
Data Index: 4002408 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.0601. Min Act: -0.1700
Data Index: 7614847 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.0432. Min Act: -0.1698
Data Index: 7535548 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.0601. Min Act: -0.1697
Data Index: 742706 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.0601. Min Act: -0.1691
Data Index: 104635 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.0432. Min Act: -0.1700
Data Index: 6908835 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.0432. Min Act: -0.1700
Data Index: 8134226 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.0432. Min Act: -0.1700
Data Index: 8447726 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.0432. Min Act: -0.1699
Data Index: 4773297 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.0601. Min Act: -0.1694
Data Index: 4469178 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2434. Min Range: -2.2434
Max Act: 2.0264. Min Act: -0.1699
Data Index: 6796086 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19