Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7017. Min Range: -9.7017
Max Act: 9.7017. Min Act: -0.1700
Data Index: 2371381 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7017. Min Range: -9.7017
Max Act: 9.5142. Min Act: -0.1700
Data Index: 6063628 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7017. Min Range: -9.7017
Max Act: 9.0142. Min Act: -0.1700
Data Index: 5778209 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7017. Min Range: -9.7017
Max Act: 8.8267. Min Act: -0.1700
Data Index: 150485 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7017. Min Range: -9.7017
Max Act: 8.8892. Min Act: -0.1700
Data Index: 5076631 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7017. Min Range: -9.7017
Max Act: 8.8892. Min Act: -0.1700
Data Index: 188314 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7017. Min Range: -9.7017
Max Act: 8.8267. Min Act: -0.1700
Data Index: 646823 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7017. Min Range: -9.7017
Max Act: 8.8267. Min Act: -0.1700
Data Index: 4542652 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7017. Min Range: -9.7017
Max Act: 8.8267. Min Act: -0.1700
Data Index: 298033 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7017. Min Range: -9.7017
Max Act: 8.8892. Min Act: -0.1700
Data Index: 4141493 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7017. Min Range: -9.7017
Max Act: 8.8892. Min Act: -0.1700
Data Index: 219011 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7017. Min Range: -9.7017
Max Act: 8.8892. Min Act: -0.1700
Data Index: 216024 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7017. Min Range: -9.7017
Max Act: 8.8892. Min Act: -0.1700
Data Index: 219009 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7017. Min Range: -9.7017
Max Act: 8.8892. Min Act: -0.1700
Data Index: 2350715 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7017. Min Range: -9.7017
Max Act: 8.8267. Min Act: -0.1700
Data Index: 216022 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7017. Min Range: -9.7017
Max Act: 8.8267. Min Act: -0.1700
Data Index: 2350717 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7017. Min Range: -9.7017
Max Act: 8.8892. Min Act: -0.1700
Data Index: 390840 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7017. Min Range: -9.7017
Max Act: 8.8267. Min Act: -0.1700
Data Index: 2210864 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7017. Min Range: -9.7017
Max Act: 8.8267. Min Act: -0.1700
Data Index: 1880291 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7017. Min Range: -9.7017
Max Act: 8.8267. Min Act: -0.1700
Data Index: 1171936 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19