Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3114 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1436. Min Range: -5.1436
Max Act: 5.1436. Min Act: -0.1700
Data Index: 6804698 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1436. Min Range: -5.1436
Max Act: 5.1436. Min Act: -0.1700
Data Index: 6839342 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1436. Min Range: -5.1436
Max Act: 5.0811. Min Act: -0.1700
Data Index: 2890776 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1436. Min Range: -5.1436
Max Act: 5.0811. Min Act: -0.1700
Data Index: 4710331 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1436. Min Range: -5.1436
Max Act: 5.0498. Min Act: -0.1700
Data Index: 6473412 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1436. Min Range: -5.1436
Max Act: 5.0498. Min Act: -0.1700
Data Index: 5914471 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1436. Min Range: -5.1436
Max Act: 5.0186. Min Act: -0.1700
Data Index: 1758904 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1436. Min Range: -5.1436
Max Act: 5.0186. Min Act: -0.1700
Data Index: 7571486 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1436. Min Range: -5.1436
Max Act: 5.0186. Min Act: -0.1700
Data Index: 3060322 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1436. Min Range: -5.1436
Max Act: 5.0498. Min Act: -0.1700
Data Index: 6643764 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1436. Min Range: -5.1436
Max Act: 5.0186. Min Act: -0.1700
Data Index: 3423856 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1436. Min Range: -5.1436
Max Act: 4.9873. Min Act: -0.1700
Data Index: 3492833 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1436. Min Range: -5.1436
Max Act: 4.9873. Min Act: -0.1700
Data Index: 610757 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1436. Min Range: -5.1436
Max Act: 4.9561. Min Act: -0.1700
Data Index: 776889 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1436. Min Range: -5.1436
Max Act: 4.9873. Min Act: -0.1700
Data Index: 4775558 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1436. Min Range: -5.1436
Max Act: 4.9873. Min Act: -0.1700
Data Index: 3826060 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1436. Min Range: -5.1436
Max Act: 4.9561. Min Act: -0.1700
Data Index: 8260714 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1436. Min Range: -5.1436
Max Act: 4.9561. Min Act: -0.1700
Data Index: 5838599 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1436. Min Range: -5.1436
Max Act: 4.9561. Min Act: -0.1700
Data Index: 4169454 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1436. Min Range: -5.1436
Max Act: 4.9248. Min Act: -0.1700
Data Index: 3878453 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19