Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2558 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3407. Min Range: -7.3407
Max Act: 7.3407. Min Act: -0.1700
Data Index: 7578354 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.8407. Min Act: -0.1700
Data Index: 7433838 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.7782. Min Act: -0.1700
Data Index: 2115969 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.7782. Min Act: -0.1700
Data Index: 3240671 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.6532. Min Act: -0.1700
Data Index: 1920173 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.6219. Min Act: -0.1700
Data Index: 5103146 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.6219. Min Act: -0.1700
Data Index: 7559560 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.5594. Min Act: -0.1700
Data Index: 6385836 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.5594. Min Act: -0.1700
Data Index: 522349 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.5282. Min Act: -0.1700
Data Index: 5159492 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.5282. Min Act: -0.1700
Data Index: 1951109 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.4657. Min Act: -0.1700
Data Index: 5509374 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.4657. Min Act: -0.1700
Data Index: 1606500 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.4344. Min Act: -0.1700
Data Index: 4496298 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.4032. Min Act: -0.1700
Data Index: 8098428 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.3719. Min Act: -0.1700
Data Index: 1644225 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.3407. Min Act: -0.1700
Data Index: 2646649 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.3407. Min Act: -0.1700
Data Index: 2493724 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.3407. Min Act: -0.1700
Data Index: 4753723 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3407. Min Range: -7.3407
Max Act: 6.3094. Min Act: -0.1700
Data Index: 7379582 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19