Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3054 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.6015. Min Act: -0.1328
Data Index: 6488214 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.3515. Min Act: -0.1618
Data Index: 4362007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.2890. Min Act: -0.1700
Data Index: 7257699 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.2265. Min Act: -0.0785
Data Index: 1314935 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.2265. Min Act: -0.1700
Data Index: 11047 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.2265. Min Act: -0.1606
Data Index: 7574938 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.2265. Min Act: -0.1693
Data Index: 3678450 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.2265. Min Act: -0.1699
Data Index: 745951 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1640. Min Act: -0.1700
Data Index: 3011958 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1015. Min Act: -0.1700
Data Index: 784266 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1640. Min Act: -0.1700
Data Index: 7257688 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1640. Min Act: -0.1700
Data Index: 2354017 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1640. Min Act: -0.1700
Data Index: 957861 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1640. Min Act: -0.1700
Data Index: 7814397 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1640. Min Act: -0.1689
Data Index: 5302330 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1640. Min Act: -0.1697
Data Index: 7814409 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1640. Min Act: -0.1667
Data Index: 8490239 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.2265. Min Act: -0.1700
Data Index: 1782782 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1640. Min Act: -0.1699
Data Index: 6116848 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6015. Min Range: -6.6015
Max Act: 6.1640. Min Act: -0.1700
Data Index: 3628745 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19