Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2345 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.9926. Min Act: -0.1700
Data Index: 135893 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.8989. Min Act: -0.1700
Data Index: 300144 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.8051. Min Act: -0.1700
Data Index: 6544263 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.7426. Min Act: -0.1700
Data Index: 851677 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.5864. Min Act: -0.1700
Data Index: 3789327 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.5239. Min Act: -0.1700
Data Index: 1061429 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.5239. Min Act: -0.1700
Data Index: 7886384 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.4926. Min Act: -0.1700
Data Index: 4069338 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.4301. Min Act: -0.1700
Data Index: 4900932 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.4301. Min Act: -0.1700
Data Index: 8204418 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.3989. Min Act: -0.1700
Data Index: 183096 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.3676. Min Act: -0.1700
Data Index: 2183234 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.3364. Min Act: -0.1700
Data Index: 6277571 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.3051. Min Act: -0.1700
Data Index: 2050616 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.3051. Min Act: -0.1700
Data Index: 388441 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.3051. Min Act: -0.1700
Data Index: 3775084 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.3364. Min Act: -0.1700
Data Index: 3163195 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.3051. Min Act: -0.1700
Data Index: 5866102 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.3051. Min Act: -0.1700
Data Index: 707658 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9926. Min Range: -6.9926
Max Act: 6.3051. Min Act: -0.1700
Data Index: 8113996 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19