Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 302 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0193. Min Range: -4.0193
Max Act: 4.0193. Min Act: -0.1700
Data Index: 8757104 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.8630. Min Act: -0.1700
Data Index: 5865083 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.8005. Min Act: -0.1700
Data Index: 5441140 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.8005. Min Act: -0.1700
Data Index: 2540317 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.8005. Min Act: -0.1700
Data Index: 8215976 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.8005. Min Act: -0.1700
Data Index: 5500820 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.7692. Min Act: -0.1700
Data Index: 5833713 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.7379. Min Act: -0.1700
Data Index: 3469273 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.6910. Min Act: -0.1700
Data Index: 5720502 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.6910. Min Act: -0.1700
Data Index: 3489024 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.6753. Min Act: -0.1700
Data Index: 36900 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.6910. Min Act: -0.1700
Data Index: 3147979 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.6753. Min Act: -0.1700
Data Index: 3424132 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.6753. Min Act: -0.1700
Data Index: 4514518 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.6597. Min Act: -0.1700
Data Index: 8421893 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.6597. Min Act: -0.1700
Data Index: 463839 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.6441. Min Act: -0.1700
Data Index: 8702459 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.6441. Min Act: -0.1700
Data Index: 5907228 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.6284. Min Act: -0.1700
Data Index: 3673106 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0193. Min Range: -4.0193
Max Act: 3.6284. Min Act: -0.1700
Data Index: 48387 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19