Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 455 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0825. Min Range: -8.0825
Max Act: 8.0825. Min Act: -0.1700
Data Index: 3970968 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.5825. Min Act: -0.1700
Data Index: 5939632 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.4262. Min Act: -0.1700
Data Index: 6626633 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.3325. Min Act: -0.1700
Data Index: 4843950 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.3012. Min Act: -0.1700
Data Index: 1344787 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.2700. Min Act: -0.1700
Data Index: 4373738 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.2075. Min Act: -0.1700
Data Index: 6127585 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.2075. Min Act: -0.1700
Data Index: 2839863 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.2075. Min Act: -0.1700
Data Index: 4246242 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.1762. Min Act: -0.1700
Data Index: 6610331 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.1762. Min Act: -0.1700
Data Index: 67055 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.1762. Min Act: -0.1700
Data Index: 8597215 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.1450. Min Act: -0.1700
Data Index: 3049837 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.1762. Min Act: -0.1700
Data Index: 5082759 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.1450. Min Act: -0.1700
Data Index: 6276505 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.1450. Min Act: -0.1700
Data Index: 8640010 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.0825. Min Act: -0.1700
Data Index: 256059 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.1450. Min Act: -0.1700
Data Index: 4551498 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.1137. Min Act: -0.1700
Data Index: 7530107 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0825. Min Range: -8.0825
Max Act: 7.0825. Min Act: -0.1700
Data Index: 5353005 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19