Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2491 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.4513. Min Act: -0.1700
Data Index: 3257004 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.3576. Min Act: -0.1700
Data Index: 5703910 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.3576. Min Act: -0.1700
Data Index: 7976752 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.2951. Min Act: -0.1698
Data Index: 1613291 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.2326. Min Act: -0.1700
Data Index: 5827368 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.2326. Min Act: -0.1697
Data Index: 6992817 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.2326. Min Act: -0.1700
Data Index: 2105889 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.2326. Min Act: -0.1698
Data Index: 3883514 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.2326. Min Act: -0.1700
Data Index: 3763226 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.2326. Min Act: -0.1700
Data Index: 5619131 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.2013. Min Act: -0.1700
Data Index: 668447 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.2013. Min Act: -0.1694
Data Index: 5112760 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.2013. Min Act: -0.1700
Data Index: 5683770 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.2013. Min Act: -0.1700
Data Index: 261716 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.2013. Min Act: -0.1700
Data Index: 523458 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.1700. Min Act: -0.1700
Data Index: 1569509 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.2013. Min Act: -0.1698
Data Index: 2678703 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.2013. Min Act: -0.1700
Data Index: 668313 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.2013. Min Act: -0.1700
Data Index: 558176 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4513. Min Range: -4.4513
Max Act: 4.2013. Min Act: -0.1700
Data Index: 908018 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19