Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4137 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2653. Min Range: -8.2653
Max Act: 8.2653. Min Act: -0.1700
Data Index: 2374650 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2653. Min Range: -8.2653
Max Act: 8.0778. Min Act: -0.1700
Data Index: 3412856 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2653. Min Range: -8.2653
Max Act: 8.0153. Min Act: -0.1700
Data Index: 5621721 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2653. Min Range: -8.2653
Max Act: 7.9528. Min Act: -0.1700
Data Index: 2578970 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2653. Min Range: -8.2653
Max Act: 7.9528. Min Act: -0.1700
Data Index: 2578992 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2653. Min Range: -8.2653
Max Act: 7.8903. Min Act: -0.1700
Data Index: 1233078 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2653. Min Range: -8.2653
Max Act: 7.8903. Min Act: -0.1700
Data Index: 7190669 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2653. Min Range: -8.2653
Max Act: 7.8278. Min Act: -0.1700
Data Index: 2657841 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2653. Min Range: -8.2653
Max Act: 7.8278. Min Act: -0.1700
Data Index: 2578995 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2653. Min Range: -8.2653
Max Act: 7.8278. Min Act: -0.1700
Data Index: 1861416 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2653. Min Range: -8.2653
Max Act: 7.7028. Min Act: -0.1700
Data Index: 1986758 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2653. Min Range: -8.2653
Max Act: 7.7028. Min Act: -0.1700
Data Index: 4621759 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2653. Min Range: -8.2653
Max Act: 7.7028. Min Act: -0.1700
Data Index: 2578994 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2653. Min Range: -8.2653
Max Act: 7.7028. Min Act: -0.1700
Data Index: 2578988 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2653. Min Range: -8.2653
Max Act: 7.7028. Min Act: -0.1700
Data Index: 2578979 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2653. Min Range: -8.2653
Max Act: 7.6403. Min Act: -0.1700
Data Index: 2578978 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2653. Min Range: -8.2653
Max Act: 7.6403. Min Act: -0.1700
Data Index: 4621760 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2653. Min Range: -8.2653
Max Act: 7.6403. Min Act: -0.1700
Data Index: 301932 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2653. Min Range: -8.2653
Max Act: 7.6403. Min Act: -0.1700
Data Index: 2578980 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2653. Min Range: -8.2653
Max Act: 7.6403. Min Act: -0.1700
Data Index: 157039 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19