Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5160 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7988. Min Range: -6.7988
Max Act: 6.7988. Min Act: -0.1700
Data Index: 4671526 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7988. Min Range: -6.7988
Max Act: 6.2675. Min Act: -0.1700
Data Index: 675405 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7988. Min Range: -6.7988
Max Act: 6.2363. Min Act: -0.1700
Data Index: 6781469 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7988. Min Range: -6.7988
Max Act: 6.1738. Min Act: -0.1700
Data Index: 3245399 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7988. Min Range: -6.7988
Max Act: 6.1425. Min Act: -0.1700
Data Index: 616485 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7988. Min Range: -6.7988
Max Act: 6.1425. Min Act: -0.1700
Data Index: 3842416 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7988. Min Range: -6.7988
Max Act: 6.0800. Min Act: -0.1700
Data Index: 4047600 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7988. Min Range: -6.7988
Max Act: 6.0488. Min Act: -0.1700
Data Index: 6067701 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7988. Min Range: -6.7988
Max Act: 6.0175. Min Act: -0.1700
Data Index: 4289214 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7988. Min Range: -6.7988
Max Act: 6.0175. Min Act: -0.1700
Data Index: 5162929 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7988. Min Range: -6.7988
Max Act: 5.9550. Min Act: -0.1700
Data Index: 5117855 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7988. Min Range: -6.7988
Max Act: 5.9863. Min Act: -0.1700
Data Index: 5319259 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7988. Min Range: -6.7988
Max Act: 5.8925. Min Act: -0.1700
Data Index: 5878749 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7988. Min Range: -6.7988
Max Act: 5.8613. Min Act: -0.1700
Data Index: 637914 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7988. Min Range: -6.7988
Max Act: 5.9238. Min Act: -0.1700
Data Index: 6216846 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7988. Min Range: -6.7988
Max Act: 5.8613. Min Act: -0.1700
Data Index: 1175633 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7988. Min Range: -6.7988
Max Act: 5.8613. Min Act: -0.1700
Data Index: 1373728 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7988. Min Range: -6.7988
Max Act: 5.8300. Min Act: -0.1700
Data Index: 1044875 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7988. Min Range: -6.7988
Max Act: 5.7988. Min Act: -0.1700
Data Index: 2145704 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7988. Min Range: -6.7988
Max Act: 5.8300. Min Act: -0.1700
Data Index: 2444395 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19