Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4657 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.3047. Min Act: -0.1700
Data Index: 2355588 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.3047. Min Act: -0.1700
Data Index: 7863836 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.2890. Min Act: -0.1700
Data Index: 1441157 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.2890. Min Act: -0.1700
Data Index: 7815280 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.2418. Min Act: -0.1700
Data Index: 6277189 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.2418. Min Act: -0.1700
Data Index: 7270760 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.2104. Min Act: -0.1700
Data Index: 4905688 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1790. Min Act: -0.1700
Data Index: 4486519 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1632. Min Act: -0.1700
Data Index: 4631396 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1790. Min Act: -0.1700
Data Index: 3645837 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1632. Min Act: -0.1700
Data Index: 2523785 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1475. Min Act: -0.1700
Data Index: 3096178 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1475. Min Act: -0.1700
Data Index: 2402638 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1160. Min Act: -0.1700
Data Index: 1856707 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1317. Min Act: -0.1700
Data Index: 3948359 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1317. Min Act: -0.1700
Data Index: 4905687 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1160. Min Act: -0.1700
Data Index: 8184309 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1002. Min Act: -0.1700
Data Index: 4858432 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1160. Min Act: -0.1700
Data Index: 4393388 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.0845. Min Act: -0.1700
Data Index: 6303871 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19