Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3991 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.8996. Min Act: -0.1700
Data Index: 2002932 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.8655. Min Act: -0.1700
Data Index: 6032270 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.8570. Min Act: -0.1700
Data Index: 3974366 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.8400. Min Act: -0.1700
Data Index: 4865074 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.8316. Min Act: -0.1700
Data Index: 3647715 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.8316. Min Act: -0.1700
Data Index: 837679 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.8316. Min Act: -0.1700
Data Index: 650324 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.8316. Min Act: -0.1700
Data Index: 6705702 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.8316. Min Act: -0.1700
Data Index: 5561728 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.8316. Min Act: -0.1700
Data Index: 5716138 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.8316. Min Act: -0.1700
Data Index: 1556864 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.8063. Min Act: -0.1700
Data Index: 6100570 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.8147. Min Act: -0.1700
Data Index: 5416330 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.8147. Min Act: -0.1700
Data Index: 8406564 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.8063. Min Act: -0.1700
Data Index: 2010472 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.7979. Min Act: -0.1700
Data Index: 929309 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.7979. Min Act: -0.1700
Data Index: 1929755 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.7979. Min Act: -0.1699
Data Index: 5832301 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.7895. Min Act: -0.1700
Data Index: 2256837 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8996. Min Range: -0.8996
Max Act: 0.7979. Min Act: -0.1700
Data Index: 3330592 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19