Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3182 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.0751. Min Range: -14.0751
Max Act: 14.0751. Min Act: -0.1700
Data Index: 4645173 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.8251. Min Act: -0.1700
Data Index: 371133 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.8251. Min Act: -0.1700
Data Index: 789333 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.8251. Min Act: -0.1700
Data Index: 4101767 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.7001. Min Act: -0.1700
Data Index: 8429308 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.6376. Min Act: -0.1700
Data Index: 7175185 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.7001. Min Act: -0.1700
Data Index: 1661476 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.6376. Min Act: -0.1700
Data Index: 4686274 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.7001. Min Act: -0.1700
Data Index: 545235 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.7001. Min Act: -0.1700
Data Index: 5936528 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.6376. Min Act: -0.1700
Data Index: 8300312 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.6376. Min Act: -0.1700
Data Index: 4628364 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.7001. Min Act: -0.1700
Data Index: 6471649 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.6376. Min Act: -0.1700
Data Index: 6653379 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.5751. Min Act: -0.1700
Data Index: 3837049 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.6376. Min Act: -0.1700
Data Index: 3317208 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.6376. Min Act: -0.1700
Data Index: 2862732 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.6376. Min Act: -0.1700
Data Index: 2562414 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.6376. Min Act: -0.1700
Data Index: 2713948 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.0751. Min Range: -14.0751
Max Act: 13.6376. Min Act: -0.1700
Data Index: 6688427 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19