Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3552 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.4637. Min Act: -0.1700
Data Index: 2956341 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.4637. Min Act: -0.1700
Data Index: 281062 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.3699. Min Act: -0.1700
Data Index: 3892354 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.3387. Min Act: -0.1700
Data Index: 5095920 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.3074. Min Act: -0.1700
Data Index: 6783519 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.2762. Min Act: -0.1700
Data Index: 8268391 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.2762. Min Act: -0.1700
Data Index: 5056422 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.2762. Min Act: -0.1700
Data Index: 6130468 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.2449. Min Act: -0.1700
Data Index: 2213631 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.2449. Min Act: -0.1700
Data Index: 6102780 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.2449. Min Act: -0.1700
Data Index: 1599697 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.2762. Min Act: -0.1700
Data Index: 8642303 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.2449. Min Act: -0.1700
Data Index: 4674703 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.2137. Min Act: -0.1700
Data Index: 798190 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.2137. Min Act: -0.1700
Data Index: 798191 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.1824. Min Act: -0.1700
Data Index: 1250589 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.1199. Min Act: -0.1700
Data Index: 7292187 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.1512. Min Act: -0.1700
Data Index: 1930879 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.1512. Min Act: -0.1700
Data Index: 896077 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4637. Min Range: -5.4637
Max Act: 5.1199. Min Act: -0.1700
Data Index: 5503737 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19