Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5641 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.5812. Min Act: -0.1700
Data Index: 7738952 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.5500. Min Act: -0.1700
Data Index: 5030910 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.5500. Min Act: -0.1700
Data Index: 7206235 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.4875. Min Act: -0.1700
Data Index: 2158874 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.5187. Min Act: -0.1700
Data Index: 8599328 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.4875. Min Act: -0.1700
Data Index: 6563192 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.4562. Min Act: -0.1700
Data Index: 930875 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.4875. Min Act: -0.1700
Data Index: 530229 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.4562. Min Act: -0.1700
Data Index: 4370559 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.4562. Min Act: -0.1700
Data Index: 5171104 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.4562. Min Act: -0.1700
Data Index: 7891630 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.4250. Min Act: -0.1700
Data Index: 5984590 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.4250. Min Act: -0.1700
Data Index: 4283704 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.4250. Min Act: -0.1700
Data Index: 1864743 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.4250. Min Act: -0.1700
Data Index: 6267286 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.4250. Min Act: -0.1700
Data Index: 6069500 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.4250. Min Act: -0.1700
Data Index: 4433717 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.4250. Min Act: -0.1700
Data Index: 6881417 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.4250. Min Act: -0.1700
Data Index: 4468859 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5812. Min Range: -5.5812
Max Act: 5.3937. Min Act: -0.1700
Data Index: 1269752 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19