Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3699 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.8596. Min Act: -0.1700
Data Index: 2434506 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.7659. Min Act: -0.1700
Data Index: 5880688 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.7346. Min Act: -0.1700
Data Index: 1522953 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.7346. Min Act: -0.1700
Data Index: 5992807 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.7034. Min Act: -0.1700
Data Index: 2101920 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.7034. Min Act: -0.1700
Data Index: 331060 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.7034. Min Act: -0.1700
Data Index: 4429762 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.6409. Min Act: -0.1700
Data Index: 8770958 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.7034. Min Act: -0.1700
Data Index: 3442248 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.6721. Min Act: -0.1700
Data Index: 2725406 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.6721. Min Act: -0.1700
Data Index: 5661543 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.6409. Min Act: -0.1700
Data Index: 8771433 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.6409. Min Act: -0.1700
Data Index: 2434522 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.6409. Min Act: -0.1700
Data Index: 467347 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.6096. Min Act: -0.1700
Data Index: 5748894 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.6096. Min Act: -0.1700
Data Index: 5678074 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.6096. Min Act: -0.1700
Data Index: 4300915 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.6096. Min Act: -0.1700
Data Index: 5464682 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.6096. Min Act: -0.1700
Data Index: 3543742 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8596. Min Range: -5.8596
Max Act: 5.6096. Min Act: -0.1700
Data Index: 254846 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19