Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2647 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.9596. Min Act: -0.1700
Data Index: 5478283 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.7408. Min Act: -0.1700
Data Index: 8336398 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.7721. Min Act: -0.1700
Data Index: 335315 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.7721. Min Act: -0.1700
Data Index: 4125248 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.6783. Min Act: -0.1700
Data Index: 4933805 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.6783. Min Act: -0.1700
Data Index: 7734084 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.6783. Min Act: -0.1700
Data Index: 8507751 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.6471. Min Act: -0.1700
Data Index: 2787542 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.6471. Min Act: -0.1700
Data Index: 3948420 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.6158. Min Act: -0.1700
Data Index: 6912671 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.6471. Min Act: -0.1700
Data Index: 321881 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.5533. Min Act: -0.1700
Data Index: 2020147 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.5533. Min Act: -0.1700
Data Index: 6766037 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.5533. Min Act: -0.1700
Data Index: 873612 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.5533. Min Act: -0.1700
Data Index: 1679758 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.5533. Min Act: -0.1700
Data Index: 6929709 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.5533. Min Act: -0.1700
Data Index: 7280502 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.5221. Min Act: -0.1700
Data Index: 5680769 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.5533. Min Act: -0.1700
Data Index: 6766035 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9596. Min Range: -5.9596
Max Act: 5.5221. Min Act: -0.1700
Data Index: 4015440 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19