Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5957 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.6185. Min Act: -0.1700
Data Index: 8483034 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.5560. Min Act: -0.1700
Data Index: 7796594 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.4310. Min Act: -0.1700
Data Index: 1407663 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.3373. Min Act: -0.1700
Data Index: 766345 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.3060. Min Act: -0.1700
Data Index: 2494391 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.3373. Min Act: -0.1700
Data Index: 498409 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.3060. Min Act: -0.1700
Data Index: 997709 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.3060. Min Act: -0.1700
Data Index: 283668 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.2748. Min Act: -0.1700
Data Index: 3907504 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.2748. Min Act: -0.1700
Data Index: 3975055 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.2435. Min Act: -0.1700
Data Index: 8230442 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.2123. Min Act: -0.1700
Data Index: 4395265 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.1810. Min Act: -0.1700
Data Index: 8145164 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.1810. Min Act: -0.1700
Data Index: 8566505 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.1810. Min Act: -0.1700
Data Index: 433425 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.1185. Min Act: -0.1700
Data Index: 4166601 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.1185. Min Act: -0.1700
Data Index: 3720793 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.1185. Min Act: -0.1700
Data Index: 8760004 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.0560. Min Act: -0.1700
Data Index: 850040 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6185. Min Range: -7.6185
Max Act: 7.0873. Min Act: -0.1700
Data Index: 6922768 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19