Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2484 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.7221. Min Act: -0.1700
Data Index: 6085359 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.7061. Min Act: -0.1700
Data Index: 1590032 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.6740. Min Act: -0.1700
Data Index: 6479389 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.6580. Min Act: -0.1700
Data Index: 3342966 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.6740. Min Act: -0.1700
Data Index: 4798731 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.6580. Min Act: -0.1700
Data Index: 1049131 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.6420. Min Act: -0.1700
Data Index: 5141376 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.6420. Min Act: -0.1700
Data Index: 8632162 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.6259. Min Act: -0.1700
Data Index: 4812049 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.6098. Min Act: -0.1700
Data Index: 4367170 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.6098. Min Act: -0.1700
Data Index: 5210757 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.6098. Min Act: -0.1700
Data Index: 6279571 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.6098. Min Act: -0.1700
Data Index: 7908584 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.6098. Min Act: -0.1700
Data Index: 568421 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.6098. Min Act: -0.1700
Data Index: 8134324 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.5937. Min Act: -0.1700
Data Index: 6789858 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.5937. Min Act: -0.1700
Data Index: 4627720 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.5937. Min Act: -0.1700
Data Index: 6688351 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.5776. Min Act: -0.1700
Data Index: 7390698 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7221. Min Range: -2.7221
Max Act: 2.5937. Min Act: -0.1700
Data Index: 1017888 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19