Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2786 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.3453. Min Act: -0.1700
Data Index: 3133851 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2828. Min Act: -0.1700
Data Index: 7430774 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2828. Min Act: -0.1700
Data Index: 8442362 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2516. Min Act: -0.1700
Data Index: 1656328 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2203. Min Act: -0.1700
Data Index: 4197812 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1891. Min Act: -0.1700
Data Index: 1250530 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1891. Min Act: -0.1700
Data Index: 620392 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1266. Min Act: -0.1700
Data Index: 8352261 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1578. Min Act: -0.1700
Data Index: 2439693 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1266. Min Act: -0.1700
Data Index: 72094 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1266. Min Act: -0.1700
Data Index: 3416633 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1266. Min Act: -0.1700
Data Index: 1398178 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1266. Min Act: -0.1700
Data Index: 3199328 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1266. Min Act: -0.1700
Data Index: 5676292 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1266. Min Act: -0.1700
Data Index: 6109619 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1266. Min Act: -0.1700
Data Index: 6250706 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1266. Min Act: -0.1700
Data Index: 1012901 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0953. Min Act: -0.1700
Data Index: 2270263 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0953. Min Act: -0.1700
Data Index: 127900 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0953. Min Act: -0.1700
Data Index: 2234492 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19