Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3230 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.9616. Min Act: -0.1700
Data Index: 3211645 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.9928. Min Act: -0.1700
Data Index: 3459575 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.9303. Min Act: -0.1700
Data Index: 761676 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.8678. Min Act: -0.1700
Data Index: 3211647 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.8678. Min Act: -0.1700
Data Index: 7262297 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.8366. Min Act: -0.1700
Data Index: 4935193 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.8366. Min Act: -0.1700
Data Index: 7983698 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.8366. Min Act: -0.1700
Data Index: 5605052 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.8366. Min Act: -0.1700
Data Index: 665789 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.8366. Min Act: -0.1700
Data Index: 4972759 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.8053. Min Act: -0.1700
Data Index: 7819905 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.8053. Min Act: -0.1700
Data Index: 5510275 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.7741. Min Act: -0.1700
Data Index: 3118236 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.7741. Min Act: -0.1700
Data Index: 6873027 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.7428. Min Act: -0.1700
Data Index: 5799628 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.7428. Min Act: -0.1700
Data Index: 1855329 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.7428. Min Act: -0.1700
Data Index: 1087408 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.7428. Min Act: -0.1700
Data Index: 3211646 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.7741. Min Act: -0.1700
Data Index: 5519094 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9928. Min Range: -4.9928
Max Act: 4.7116. Min Act: -0.1700
Data Index: 8098720 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19