Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5436 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.1266. Min Range: -16.1266
Max Act: 16.1266. Min Act: -0.1700
Data Index: 1834547 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.1266. Min Range: -16.1266
Max Act: 15.3766. Min Act: -0.1700
Data Index: 4259312 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.1266. Min Range: -16.1266
Max Act: 15.5016. Min Act: -0.1700
Data Index: 3701271 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.1266. Min Range: -16.1266
Max Act: 15.3141. Min Act: -0.1700
Data Index: 2333159 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.1266. Min Range: -16.1266
Max Act: 15.1891. Min Act: -0.1700
Data Index: 3649458 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.1266. Min Range: -16.1266
Max Act: 15.1266. Min Act: -0.1700
Data Index: 6564149 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.1266. Min Range: -16.1266
Max Act: 15.0641. Min Act: -0.1700
Data Index: 7495134 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.1266. Min Range: -16.1266
Max Act: 15.0016. Min Act: -0.1700
Data Index: 2288689 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.1266. Min Range: -16.1266
Max Act: 14.9391. Min Act: -0.1700
Data Index: 1440064 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.1266. Min Range: -16.1266
Max Act: 14.9391. Min Act: -0.1700
Data Index: 3260590 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.1266. Min Range: -16.1266
Max Act: 14.9391. Min Act: -0.1700
Data Index: 3065802 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.1266. Min Range: -16.1266
Max Act: 14.8766. Min Act: -0.1700
Data Index: 2708983 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.1266. Min Range: -16.1266
Max Act: 14.8141. Min Act: -0.1700
Data Index: 3212797 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.1266. Min Range: -16.1266
Max Act: 14.8141. Min Act: -0.1700
Data Index: 3833927 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.1266. Min Range: -16.1266
Max Act: 14.7516. Min Act: -0.1700
Data Index: 6538029 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.1266. Min Range: -16.1266
Max Act: 14.7516. Min Act: -0.1700
Data Index: 4309978 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.1266. Min Range: -16.1266
Max Act: 14.7516. Min Act: -0.1700
Data Index: 1073645 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.1266. Min Range: -16.1266
Max Act: 14.7516. Min Act: -0.1700
Data Index: 6819072 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.1266. Min Range: -16.1266
Max Act: 14.8141. Min Act: -0.1700
Data Index: 7126724 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.1266. Min Range: -16.1266
Max Act: 14.7516. Min Act: -0.1700
Data Index: 6092454 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19