Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4056 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5073. Min Range: -8.5073
Max Act: 8.5073. Min Act: -0.1700
Data Index: 7717881 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5073. Min Range: -8.5073
Max Act: 8.3823. Min Act: -0.1700
Data Index: 941375 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5073. Min Range: -8.5073
Max Act: 8.2573. Min Act: -0.1700
Data Index: 4381512 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5073. Min Range: -8.5073
Max Act: 8.1948. Min Act: -0.1700
Data Index: 2101693 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5073. Min Range: -8.5073
Max Act: 8.1948. Min Act: -0.1700
Data Index: 1529490 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5073. Min Range: -8.5073
Max Act: 8.0698. Min Act: -0.1700
Data Index: 1107095 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5073. Min Range: -8.5073
Max Act: 8.0698. Min Act: -0.1700
Data Index: 8739372 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5073. Min Range: -8.5073
Max Act: 8.0073. Min Act: -0.1700
Data Index: 4073675 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5073. Min Range: -8.5073
Max Act: 8.0073. Min Act: -0.1700
Data Index: 1449172 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5073. Min Range: -8.5073
Max Act: 8.0073. Min Act: -0.1700
Data Index: 2886532 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5073. Min Range: -8.5073
Max Act: 7.9448. Min Act: -0.1700
Data Index: 7257502 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5073. Min Range: -8.5073
Max Act: 7.8823. Min Act: -0.1700
Data Index: 6920841 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5073. Min Range: -8.5073
Max Act: 7.8823. Min Act: -0.1700
Data Index: 597835 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5073. Min Range: -8.5073
Max Act: 7.8823. Min Act: -0.1700
Data Index: 6853379 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5073. Min Range: -8.5073
Max Act: 7.8198. Min Act: -0.1700
Data Index: 5999643 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5073. Min Range: -8.5073
Max Act: 7.8198. Min Act: -0.1700
Data Index: 7321349 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5073. Min Range: -8.5073
Max Act: 7.8198. Min Act: -0.1700
Data Index: 5043034 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5073. Min Range: -8.5073
Max Act: 7.8198. Min Act: -0.1700
Data Index: 3578574 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5073. Min Range: -8.5073
Max Act: 7.7573. Min Act: -0.1700
Data Index: 1387666 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5073. Min Range: -8.5073
Max Act: 7.7573. Min Act: -0.1700
Data Index: 4981278 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19