Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3615 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1911. Min Range: -8.1911
Max Act: 8.1911. Min Act: -0.1700
Data Index: 7740599 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1911. Min Range: -8.1911
Max Act: 7.4411. Min Act: -0.1700
Data Index: 2983632 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1911. Min Range: -8.1911
Max Act: 7.3473. Min Act: -0.1700
Data Index: 5630 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1911. Min Range: -8.1911
Max Act: 7.3161. Min Act: -0.1700
Data Index: 960440 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1911. Min Range: -8.1911
Max Act: 7.2848. Min Act: -0.1700
Data Index: 1410965 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1911. Min Range: -8.1911
Max Act: 7.2536. Min Act: -0.1700
Data Index: 1791367 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1911. Min Range: -8.1911
Max Act: 7.0661. Min Act: -0.1700
Data Index: 4196953 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1911. Min Range: -8.1911
Max Act: 7.0348. Min Act: -0.1700
Data Index: 7938012 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1911. Min Range: -8.1911
Max Act: 7.0348. Min Act: -0.1700
Data Index: 2829965 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1911. Min Range: -8.1911
Max Act: 7.0036. Min Act: -0.1700
Data Index: 4879613 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1911. Min Range: -8.1911
Max Act: 6.9723. Min Act: -0.1700
Data Index: 2529310 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1911. Min Range: -8.1911
Max Act: 6.9098. Min Act: -0.1700
Data Index: 702133 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1911. Min Range: -8.1911
Max Act: 6.9098. Min Act: -0.1700
Data Index: 6493876 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1911. Min Range: -8.1911
Max Act: 6.8473. Min Act: -0.1700
Data Index: 3865329 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1911. Min Range: -8.1911
Max Act: 6.8473. Min Act: -0.1700
Data Index: 5515625 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1911. Min Range: -8.1911
Max Act: 6.8473. Min Act: -0.1700
Data Index: 6700677 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1911. Min Range: -8.1911
Max Act: 6.8161. Min Act: -0.1700
Data Index: 1755766 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1911. Min Range: -8.1911
Max Act: 6.8161. Min Act: -0.1700
Data Index: 5110588 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1911. Min Range: -8.1911
Max Act: 6.7848. Min Act: -0.1700
Data Index: 2651435 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1911. Min Range: -8.1911
Max Act: 6.7848. Min Act: -0.1700
Data Index: 5095803 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19