Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5219 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0991. Min Range: -5.0991
Max Act: 5.0991. Min Act: -0.1700
Data Index: 6527623 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0991. Min Range: -5.0991
Max Act: 5.0678. Min Act: -0.1700
Data Index: 8520668 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0991. Min Range: -5.0991
Max Act: 5.0678. Min Act: -0.1700
Data Index: 1521257 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.9116. Min Act: -0.1700
Data Index: 96989 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.9116. Min Act: -0.1700
Data Index: 8060564 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.8178. Min Act: -0.1700
Data Index: 4063088 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.7866. Min Act: -0.1700
Data Index: 6808869 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.7866. Min Act: -0.1700
Data Index: 18577 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.7866. Min Act: -0.1700
Data Index: 7830956 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.7866. Min Act: -0.1700
Data Index: 18567 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.7553. Min Act: -0.1700
Data Index: 2676537 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.7553. Min Act: -0.1700
Data Index: 5657799 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.7866. Min Act: -0.1700
Data Index: 2621169 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.7553. Min Act: -0.1700
Data Index: 3648870 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.7241. Min Act: -0.1700
Data Index: 7181001 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.7553. Min Act: -0.1700
Data Index: 7230146 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.7241. Min Act: -0.1700
Data Index: 3590668 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.7241. Min Act: -0.1700
Data Index: 6900997 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.7241. Min Act: -0.1700
Data Index: 2259657 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.6928. Min Act: -0.1700
Data Index: 3437809 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19