Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 790 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5792. Min Range: -5.5792
Max Act: 5.5792. Min Act: -0.1700
Data Index: 3163141 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5792. Min Range: -5.5792
Max Act: 5.4229. Min Act: -0.1700
Data Index: 6481197 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5792. Min Range: -5.5792
Max Act: 5.3292. Min Act: -0.1700
Data Index: 517540 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5792. Min Range: -5.5792
Max Act: 5.3292. Min Act: -0.1700
Data Index: 7447104 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5792. Min Range: -5.5792
Max Act: 5.2667. Min Act: -0.1700
Data Index: 4371189 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5792. Min Range: -5.5792
Max Act: 5.2042. Min Act: -0.1700
Data Index: 5995901 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5792. Min Range: -5.5792
Max Act: 5.2042. Min Act: -0.1700
Data Index: 870244 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5792. Min Range: -5.5792
Max Act: 5.1417. Min Act: -0.1700
Data Index: 2830833 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5792. Min Range: -5.5792
Max Act: 5.1104. Min Act: -0.1700
Data Index: 442945 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5792. Min Range: -5.5792
Max Act: 5.1417. Min Act: -0.1700
Data Index: 700871 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5792. Min Range: -5.5792
Max Act: 5.1104. Min Act: -0.1700
Data Index: 8683896 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5792. Min Range: -5.5792
Max Act: 5.0792. Min Act: -0.1700
Data Index: 6044742 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5792. Min Range: -5.5792
Max Act: 5.0479. Min Act: -0.1700
Data Index: 5465916 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5792. Min Range: -5.5792
Max Act: 5.0167. Min Act: -0.1700
Data Index: 5375849 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5792. Min Range: -5.5792
Max Act: 5.0167. Min Act: -0.1700
Data Index: 8448426 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5792. Min Range: -5.5792
Max Act: 4.9854. Min Act: -0.1700
Data Index: 4741903 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5792. Min Range: -5.5792
Max Act: 4.9854. Min Act: -0.1700
Data Index: 8390404 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5792. Min Range: -5.5792
Max Act: 4.9542. Min Act: -0.1700
Data Index: 6636996 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5792. Min Range: -5.5792
Max Act: 4.9854. Min Act: -0.1700
Data Index: 2318501 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5792. Min Range: -5.5792
Max Act: 4.9229. Min Act: -0.1700
Data Index: 3553822 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19