Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3325 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1063. Min Range: -3.1063
Max Act: 3.1063. Min Act: -0.1700
Data Index: 3247896 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1063. Min Range: -3.1063
Max Act: 3.0432. Min Act: -0.1700
Data Index: 6566553 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1063. Min Range: -3.1063
Max Act: 3.0274. Min Act: -0.1700
Data Index: 6338186 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1063. Min Range: -3.1063
Max Act: 3.0116. Min Act: -0.1700
Data Index: 8726736 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1063. Min Range: -3.1063
Max Act: 2.9958. Min Act: -0.1700
Data Index: 109295 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1063. Min Range: -3.1063
Max Act: 2.9800. Min Act: -0.1700
Data Index: 7197361 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1063. Min Range: -3.1063
Max Act: 2.9800. Min Act: -0.1700
Data Index: 3760355 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1063. Min Range: -3.1063
Max Act: 2.9642. Min Act: -0.1700
Data Index: 3923906 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1063. Min Range: -3.1063
Max Act: 2.9642. Min Act: -0.1700
Data Index: 4140363 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1063. Min Range: -3.1063
Max Act: 2.9325. Min Act: -0.1700
Data Index: 5307698 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1063. Min Range: -3.1063
Max Act: 2.8691. Min Act: -0.1700
Data Index: 114749 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1063. Min Range: -3.1063
Max Act: 2.9167. Min Act: -0.1700
Data Index: 7185220 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1063. Min Range: -3.1063
Max Act: 2.9008. Min Act: -0.1700
Data Index: 5469803 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1063. Min Range: -3.1063
Max Act: 2.9008. Min Act: -0.1700
Data Index: 1667365 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1063. Min Range: -3.1063
Max Act: 2.8850. Min Act: -0.1700
Data Index: 251233 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1063. Min Range: -3.1063
Max Act: 2.8850. Min Act: -0.1700
Data Index: 6715911 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1063. Min Range: -3.1063
Max Act: 2.9008. Min Act: -0.1700
Data Index: 7472323 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1063. Min Range: -3.1063
Max Act: 2.8850. Min Act: -0.1700
Data Index: 6111885 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1063. Min Range: -3.1063
Max Act: 2.9167. Min Act: -0.1700
Data Index: 5363216 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1063. Min Range: -3.1063
Max Act: 2.8850. Min Act: -0.1700
Data Index: 3150359 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19