Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2212 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.9797. Min Act: -0.1700
Data Index: 519158 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.9485. Min Act: -0.1700
Data Index: 8706895 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.8235. Min Act: -0.1700
Data Index: 7298406 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.7922. Min Act: -0.1700
Data Index: 4442589 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.8235. Min Act: -0.1700
Data Index: 5951822 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.7610. Min Act: -0.1700
Data Index: 764487 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.7297. Min Act: -0.1700
Data Index: 8497305 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.7610. Min Act: -0.1700
Data Index: 8525185 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.7297. Min Act: -0.1700
Data Index: 1793960 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.7610. Min Act: -0.1700
Data Index: 358202 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.7610. Min Act: -0.1700
Data Index: 7730345 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.7297. Min Act: -0.1700
Data Index: 7091507 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.7297. Min Act: -0.1700
Data Index: 1306680 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.7297. Min Act: -0.1700
Data Index: 8238323 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.7297. Min Act: -0.1700
Data Index: 3478069 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.6672. Min Act: -0.1700
Data Index: 2484799 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.6985. Min Act: -0.1700
Data Index: 1770166 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.6985. Min Act: -0.1700
Data Index: 3211457 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.6985. Min Act: -0.1700
Data Index: 7621662 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9797. Min Range: -5.9797
Max Act: 5.6985. Min Act: -0.1700
Data Index: 7107418 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19