Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2027. Min Range: -8.2027
Max Act: 8.2027. Min Act: -0.1700
Data Index: 701364 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2027. Min Range: -8.2027
Max Act: 8.0152. Min Act: -0.1700
Data Index: 1021515 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.8902. Min Act: -0.1700
Data Index: 1115258 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.9527. Min Act: -0.1700
Data Index: 1814697 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.8902. Min Act: -0.1700
Data Index: 2586126 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.8902. Min Act: -0.1700
Data Index: 1546591 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.8277. Min Act: -0.1700
Data Index: 6845142 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.7652. Min Act: -0.1700
Data Index: 3586601 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.7652. Min Act: -0.1700
Data Index: 8367657 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.7652. Min Act: -0.1700
Data Index: 2520409 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.7652. Min Act: -0.1700
Data Index: 921266 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.7027. Min Act: -0.1700
Data Index: 6149746 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.6715. Min Act: -0.1700
Data Index: 3421457 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.6715. Min Act: -0.1700
Data Index: 661123 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.6402. Min Act: -0.1700
Data Index: 3872847 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.5777. Min Act: -0.1700
Data Index: 4519430 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.5777. Min Act: -0.1700
Data Index: 345680 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.6090. Min Act: -0.1700
Data Index: 7206350 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.5777. Min Act: -0.1700
Data Index: 5549495 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2027. Min Range: -8.2027
Max Act: 7.5465. Min Act: -0.1700
Data Index: 823964 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19