Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1318 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 15.1921. Min Range: -15.1921
Max Act: 15.1921. Min Act: -0.1700
Data Index: 4164877 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.1921. Min Range: -15.1921
Max Act: 15.0671. Min Act: -0.1700
Data Index: 6981937 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.1921. Min Range: -15.1921
Max Act: 15.0046. Min Act: -0.1700
Data Index: 539902 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.1921. Min Range: -15.1921
Max Act: 15.0046. Min Act: -0.1700
Data Index: 1917913 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.1921. Min Range: -15.1921
Max Act: 14.7546. Min Act: -0.1700
Data Index: 1055822 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.1921. Min Range: -15.1921
Max Act: 14.6921. Min Act: -0.1700
Data Index: 7286100 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.1921. Min Range: -15.1921
Max Act: 14.6296. Min Act: -0.1700
Data Index: 3459242 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.1921. Min Range: -15.1921
Max Act: 14.6296. Min Act: -0.1700
Data Index: 2921065 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.1921. Min Range: -15.1921
Max Act: 14.5046. Min Act: -0.1700
Data Index: 2535669 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.1921. Min Range: -15.1921
Max Act: 14.5046. Min Act: -0.1700
Data Index: 6571932 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.1921. Min Range: -15.1921
Max Act: 14.5046. Min Act: -0.1700
Data Index: 2921066 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.1921. Min Range: -15.1921
Max Act: 14.3796. Min Act: -0.1700
Data Index: 75014 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.1921. Min Range: -15.1921
Max Act: 14.4421. Min Act: -0.1700
Data Index: 7778988 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.1921. Min Range: -15.1921
Max Act: 14.4421. Min Act: -0.1700
Data Index: 5791134 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.1921. Min Range: -15.1921
Max Act: 14.3796. Min Act: -0.1700
Data Index: 2013623 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.1921. Min Range: -15.1921
Max Act: 14.3796. Min Act: -0.1700
Data Index: 1586103 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.1921. Min Range: -15.1921
Max Act: 14.3796. Min Act: -0.1700
Data Index: 1808951 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.1921. Min Range: -15.1921
Max Act: 14.3796. Min Act: -0.1700
Data Index: 2910581 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.1921. Min Range: -15.1921
Max Act: 14.3796. Min Act: -0.1700
Data Index: 3404402 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.1921. Min Range: -15.1921
Max Act: 14.3171. Min Act: -0.1700
Data Index: 1170719 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19