Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0223. Min Range: -4.0223
Max Act: 4.0223. Min Act: -0.1700
Data Index: 4230561 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0223. Min Range: -4.0223
Max Act: 4.0223. Min Act: -0.1700
Data Index: 863320 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.9910. Min Act: -0.1700
Data Index: 461439 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.9597. Min Act: -0.1700
Data Index: 4537723 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.9597. Min Act: -0.1700
Data Index: 7633511 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.9910. Min Act: -0.1700
Data Index: 4631732 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.9285. Min Act: -0.1700
Data Index: 5198736 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.9285. Min Act: -0.1700
Data Index: 5773013 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.9285. Min Act: -0.1700
Data Index: 5102047 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.9285. Min Act: -0.1700
Data Index: 4960701 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.9285. Min Act: -0.1700
Data Index: 8247465 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.9285. Min Act: -0.1700
Data Index: 217837 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8972. Min Act: -0.1700
Data Index: 1791386 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.9285. Min Act: -0.1700
Data Index: 6909086 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8972. Min Act: -0.1700
Data Index: 1900081 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.9285. Min Act: -0.1700
Data Index: 4688229 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8972. Min Act: -0.1700
Data Index: 4397671 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8972. Min Act: -0.1700
Data Index: 3736140 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8972. Min Act: -0.1700
Data Index: 7188848 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0223. Min Range: -4.0223
Max Act: 3.8972. Min Act: -0.1700
Data Index: 8314267 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19