Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5874 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.8330. Min Act: -0.1700
Data Index: 3409789 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.8330. Min Act: -0.1700
Data Index: 2080251 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.7235. Min Act: -0.1700
Data Index: 1982341 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.6923. Min Act: -0.1700
Data Index: 7528635 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.6923. Min Act: -0.1700
Data Index: 3358895 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.6766. Min Act: -0.1700
Data Index: 5040227 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.6923. Min Act: -0.1700
Data Index: 724525 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.6453. Min Act: -0.1700
Data Index: 4980808 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.6297. Min Act: -0.1700
Data Index: 3335804 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.6140. Min Act: -0.1700
Data Index: 5935606 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.6297. Min Act: -0.1700
Data Index: 7222173 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.5984. Min Act: -0.1700
Data Index: 2754069 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.5984. Min Act: -0.1700
Data Index: 5655940 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.5671. Min Act: -0.1700
Data Index: 7385953 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.5514. Min Act: -0.1700
Data Index: 4162918 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.5671. Min Act: -0.1700
Data Index: 2531882 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.5358. Min Act: -0.1700
Data Index: 7890754 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.5201. Min Act: -0.1700
Data Index: 5655941 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.5358. Min Act: -0.1700
Data Index: 1086593 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8330. Min Range: -3.8330
Max Act: 3.5201. Min Act: -0.1700
Data Index: 5299523 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19