Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2277 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.9627. Min Act: -0.1700
Data Index: 2789702 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.8861. Min Act: -0.1697
Data Index: 2713623 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.8861. Min Act: -0.1695
Data Index: 2901840 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.8776. Min Act: -0.1635
Data Index: 4917518 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.8776. Min Act: -0.1699
Data Index: 2901842 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.8690. Min Act: -0.1695
Data Index: 6045754 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.8090. Min Act: -0.1696
Data Index: 3683103 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.8004. Min Act: -0.1700
Data Index: 3840448 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.8004. Min Act: -0.1698
Data Index: 4661923 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.7832. Min Act: -0.1665
Data Index: 3913027 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.7832. Min Act: -0.1700
Data Index: 4661921 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.7746. Min Act: -0.1693
Data Index: 744488 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.7832. Min Act: -0.1700
Data Index: 3535346 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.7660. Min Act: -0.1700
Data Index: 5236636 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.7746. Min Act: -0.1700
Data Index: 2706430 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.7573. Min Act: -0.1693
Data Index: 5845325 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.7660. Min Act: -0.1700
Data Index: 6469531 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.7573. Min Act: -0.1689
Data Index: 5382445 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.7660. Min Act: -0.1700
Data Index: 5428379 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9627. Min Range: -1.9627
Max Act: 1.7573. Min Act: -0.1700
Data Index: 2226740 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19