Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3160 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.9173. Min Act: -0.1700
Data Index: 7638125 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.9173. Min Act: -0.1700
Data Index: 2228899 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.8548. Min Act: -0.1700
Data Index: 3765515 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.8548. Min Act: -0.1700
Data Index: 8432696 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.8548. Min Act: -0.1700
Data Index: 3870609 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.7923. Min Act: -0.1700
Data Index: 1290598 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.7923. Min Act: -0.1700
Data Index: 7579635 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.7298. Min Act: -0.1700
Data Index: 7595749 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.7298. Min Act: -0.1700
Data Index: 1231687 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.7298. Min Act: -0.1700
Data Index: 3002180 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.7298. Min Act: -0.1700
Data Index: 5871031 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.6048. Min Act: -0.1700
Data Index: 7333853 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.6048. Min Act: -0.1700
Data Index: 8594781 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.6048. Min Act: -0.1700
Data Index: 8023145 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.6048. Min Act: -0.1700
Data Index: 5651515 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.6673. Min Act: -0.1700
Data Index: 1322513 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.5423. Min Act: -0.1700
Data Index: 3392266 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.5423. Min Act: -0.1700
Data Index: 5797148 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.5423. Min Act: -0.1700
Data Index: 6641060 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9173. Min Range: -9.9173
Max Act: 9.5423. Min Act: -0.1700
Data Index: 6821838 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19