Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2615 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.2122. Min Act: -0.1700
Data Index: 1322583 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.2122. Min Act: -0.1700
Data Index: 727245 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.1965. Min Act: -0.1700
Data Index: 7330764 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.1965. Min Act: -0.1700
Data Index: 6818026 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.1336. Min Act: -0.1700
Data Index: 6753965 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.1336. Min Act: -0.1700
Data Index: 6092824 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.1336. Min Act: -0.1700
Data Index: 5941779 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.1021. Min Act: -0.1700
Data Index: 2365774 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.0863. Min Act: -0.1700
Data Index: 2515846 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.0863. Min Act: -0.1700
Data Index: 6102612 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.0863. Min Act: -0.1700
Data Index: 2564895 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.0863. Min Act: -0.1700
Data Index: 95069 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.0705. Min Act: -0.1700
Data Index: 6210936 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.0705. Min Act: -0.1700
Data Index: 3347422 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.0863. Min Act: -0.1700
Data Index: 603590 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.0548. Min Act: -0.1700
Data Index: 3515349 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.0548. Min Act: -0.1700
Data Index: 3606829 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.0390. Min Act: -0.1700
Data Index: 4173766 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.0548. Min Act: -0.1700
Data Index: 4456175 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2122. Min Range: -3.2122
Max Act: 3.0548. Min Act: -0.1700
Data Index: 4895851 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19