Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2580 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3156. Min Range: -8.3156
Max Act: 8.3156. Min Act: -0.1700
Data Index: 6149473 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3156. Min Range: -8.3156
Max Act: 8.1906. Min Act: -0.1700
Data Index: 2787998 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3156. Min Range: -8.3156
Max Act: 8.1906. Min Act: -0.1700
Data Index: 7999840 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3156. Min Range: -8.3156
Max Act: 8.0031. Min Act: -0.1700
Data Index: 5537414 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3156. Min Range: -8.3156
Max Act: 8.0031. Min Act: -0.1700
Data Index: 3327405 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3156. Min Range: -8.3156
Max Act: 7.9406. Min Act: -0.1700
Data Index: 8824109 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3156. Min Range: -8.3156
Max Act: 7.8781. Min Act: -0.1700
Data Index: 7146747 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3156. Min Range: -8.3156
Max Act: 7.8781. Min Act: -0.1700
Data Index: 7746795 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3156. Min Range: -8.3156
Max Act: 7.8156. Min Act: -0.1700
Data Index: 2857724 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3156. Min Range: -8.3156
Max Act: 7.8156. Min Act: -0.1700
Data Index: 761716 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3156. Min Range: -8.3156
Max Act: 7.8156. Min Act: -0.1700
Data Index: 6086765 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3156. Min Range: -8.3156
Max Act: 7.7531. Min Act: -0.1700
Data Index: 3786021 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3156. Min Range: -8.3156
Max Act: 7.7531. Min Act: -0.1700
Data Index: 5147037 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3156. Min Range: -8.3156
Max Act: 7.6906. Min Act: -0.1700
Data Index: 3373745 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3156. Min Range: -8.3156
Max Act: 7.6906. Min Act: -0.1700
Data Index: 5291327 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3156. Min Range: -8.3156
Max Act: 7.6281. Min Act: -0.1700
Data Index: 6372838 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3156. Min Range: -8.3156
Max Act: 7.6281. Min Act: -0.1700
Data Index: 1388373 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3156. Min Range: -8.3156
Max Act: 7.6281. Min Act: -0.1700
Data Index: 8607466 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3156. Min Range: -8.3156
Max Act: 7.6281. Min Act: -0.1700
Data Index: 8607667 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3156. Min Range: -8.3156
Max Act: 7.6281. Min Act: -0.1700
Data Index: 4074323 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19