Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3587 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.9719. Min Act: -0.1700
Data Index: 8378532 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.8781. Min Act: -0.1700
Data Index: 274008 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.7844. Min Act: -0.1700
Data Index: 1454887 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.8156. Min Act: -0.1700
Data Index: 111715 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.7531. Min Act: -0.1700
Data Index: 818377 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.7531. Min Act: -0.1700
Data Index: 1750309 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.7531. Min Act: -0.1700
Data Index: 3874454 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.7531. Min Act: -0.1700
Data Index: 4218364 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.7531. Min Act: -0.1700
Data Index: 3828738 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.6906. Min Act: -0.1700
Data Index: 1093941 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.6906. Min Act: -0.1695
Data Index: 6669206 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.7219. Min Act: -0.1700
Data Index: 2247079 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.6906. Min Act: -0.1700
Data Index: 1651842 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.7219. Min Act: -0.1700
Data Index: 6221493 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.7219. Min Act: -0.1700
Data Index: 1178652 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.6906. Min Act: -0.1700
Data Index: 4478424 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.6906. Min Act: -0.1700
Data Index: 443132 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.6906. Min Act: -0.1700
Data Index: 4288634 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.6906. Min Act: -0.1700
Data Index: 5861667 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9719. Min Range: -5.9719
Max Act: 5.6906. Min Act: -0.1700
Data Index: 5519486 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19