Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5670 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.9644. Min Act: -0.1700
Data Index: 2129026 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.9644. Min Act: -0.1700
Data Index: 5371935 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.8394. Min Act: -0.1700
Data Index: 7591648 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.8394. Min Act: -0.1700
Data Index: 6379522 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.8394. Min Act: -0.1700
Data Index: 8727460 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.7769. Min Act: -0.1700
Data Index: 2731697 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.7144. Min Act: -0.1700
Data Index: 8750263 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.7144. Min Act: -0.1700
Data Index: 931866 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.7144. Min Act: -0.1700
Data Index: 3894655 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.7144. Min Act: -0.1700
Data Index: 5757716 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.6519. Min Act: -0.1699
Data Index: 5003178 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.6519. Min Act: -0.1700
Data Index: 4609609 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.6519. Min Act: -0.1700
Data Index: 5477761 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.6519. Min Act: -0.1700
Data Index: 8671560 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.6206. Min Act: -0.1700
Data Index: 1512923 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.7144. Min Act: -0.1700
Data Index: 8254520 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.6519. Min Act: -0.1700
Data Index: 7591637 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.6519. Min Act: -0.1700
Data Index: 5566443 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.6206. Min Act: -0.1700
Data Index: 5188999 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9644. Min Range: -8.9644
Max Act: 8.6206. Min Act: -0.1700
Data Index: 7281291 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19