Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3523 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.5418. Min Act: -0.1700
Data Index: 6288430 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.5418. Min Act: -0.1700
Data Index: 1088246 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.4481. Min Act: -0.1700
Data Index: 5446475 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.3856. Min Act: -0.1700
Data Index: 156854 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.3543. Min Act: -0.1700
Data Index: 3555711 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.3543. Min Act: -0.1700
Data Index: 647669 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.2918. Min Act: -0.1700
Data Index: 6283257 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.2918. Min Act: -0.1700
Data Index: 4775481 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.2606. Min Act: -0.1700
Data Index: 894943 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.2606. Min Act: -0.1700
Data Index: 2379787 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.2293. Min Act: -0.1700
Data Index: 7298837 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.1981. Min Act: -0.1700
Data Index: 1541376 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.1668. Min Act: -0.1700
Data Index: 528892 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.1668. Min Act: -0.1700
Data Index: 4459516 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.1668. Min Act: -0.1700
Data Index: 8295613 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.1356. Min Act: -0.1700
Data Index: 5781428 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.1356. Min Act: -0.1700
Data Index: 1103201 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.1356. Min Act: -0.1700
Data Index: 8546815 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.1043. Min Act: -0.1700
Data Index: 7003071 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5418. Min Range: -6.5418
Max Act: 6.1043. Min Act: -0.1700
Data Index: 4931186 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19