Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4335 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.9385. Min Act: -0.1700
Data Index: 760743 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.8448. Min Act: -0.1700
Data Index: 2091021 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.5635. Min Act: -0.1700
Data Index: 670601 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.4385. Min Act: -0.1700
Data Index: 6180931 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.4073. Min Act: -0.1700
Data Index: 8626561 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.3448. Min Act: -0.1700
Data Index: 7266712 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.3135. Min Act: -0.1700
Data Index: 564550 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.3135. Min Act: -0.1700
Data Index: 6599884 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.2823. Min Act: -0.1700
Data Index: 4648350 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.2198. Min Act: -0.1700
Data Index: 1453668 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.2510. Min Act: -0.1700
Data Index: 4781507 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.2510. Min Act: -0.1700
Data Index: 8815531 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.1885. Min Act: -0.1700
Data Index: 4955107 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.1573. Min Act: -0.1700
Data Index: 1537964 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.1885. Min Act: -0.1700
Data Index: 8578219 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.1260. Min Act: -0.1700
Data Index: 8619640 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.1573. Min Act: -0.1700
Data Index: 2125947 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.1573. Min Act: -0.1700
Data Index: 7118825 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.1260. Min Act: -0.1700
Data Index: 1787002 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9385. Min Range: -6.9385
Max Act: 6.0948. Min Act: -0.1700
Data Index: 1601062 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19