Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3326 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.8684. Min Act: -0.1700
Data Index: 7203047 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.8371. Min Act: -0.1700
Data Index: 8676297 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.8059. Min Act: -0.1700
Data Index: 461834 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.8059. Min Act: -0.1700
Data Index: 461835 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.8059. Min Act: -0.1700
Data Index: 5866185 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.8059. Min Act: -0.1700
Data Index: 5098667 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.7746. Min Act: -0.1700
Data Index: 6411153 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.7746. Min Act: -0.1700
Data Index: 3129503 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.7746. Min Act: -0.1700
Data Index: 34595 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.7746. Min Act: -0.1700
Data Index: 5099144 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.7746. Min Act: -0.1700
Data Index: 5133493 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.7434. Min Act: -0.1700
Data Index: 4322833 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.7434. Min Act: -0.1700
Data Index: 5979625 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.7434. Min Act: -0.1700
Data Index: 2969509 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.7434. Min Act: -0.1700
Data Index: 4032150 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.7434. Min Act: -0.1700
Data Index: 351166 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.7434. Min Act: -0.1700
Data Index: 3635163 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.7434. Min Act: -0.1700
Data Index: 436884 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.7434. Min Act: -0.1700
Data Index: 2452377 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8684. Min Range: -4.8684
Max Act: 4.7434. Min Act: -0.1700
Data Index: 2201591 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19