Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2626 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.8458. Min Act: -0.1700
Data Index: 2612859 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.8145. Min Act: -0.1700
Data Index: 1205337 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.7833. Min Act: -0.1700
Data Index: 2326436 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.7208. Min Act: -0.1700
Data Index: 3346673 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.6895. Min Act: -0.1700
Data Index: 7895501 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.6270. Min Act: -0.1700
Data Index: 1513501 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.5958. Min Act: -0.1700
Data Index: 7440044 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.5958. Min Act: -0.1700
Data Index: 5266102 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.5958. Min Act: -0.1700
Data Index: 1392645 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.5958. Min Act: -0.1700
Data Index: 5230851 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.5958. Min Act: -0.1700
Data Index: 3903454 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.5333. Min Act: -0.1700
Data Index: 3445251 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.5333. Min Act: -0.1700
Data Index: 629547 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.5333. Min Act: -0.1700
Data Index: 885769 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.5020. Min Act: -0.1700
Data Index: 7212746 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.5020. Min Act: -0.1700
Data Index: 4641933 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.5020. Min Act: -0.1700
Data Index: 3112504 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.5020. Min Act: -0.1700
Data Index: 7411568 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.4708. Min Act: -0.1700
Data Index: 6386892 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8458. Min Range: -6.8458
Max Act: 6.4708. Min Act: -0.1700
Data Index: 4032644 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19