Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2947 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.9499. Min Act: -0.1700
Data Index: 2134990 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.8874. Min Act: -0.1700
Data Index: 2134991 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.6061. Min Act: -0.1700
Data Index: 7044500 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.3874. Min Act: -0.1700
Data Index: 3468874 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.2624. Min Act: -0.1700
Data Index: 630550 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.2936. Min Act: -0.1700
Data Index: 7819411 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.2624. Min Act: -0.1700
Data Index: 7164598 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.2311. Min Act: -0.1700
Data Index: 7149433 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.1999. Min Act: -0.1700
Data Index: 8726398 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.1999. Min Act: -0.1700
Data Index: 195372 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.1686. Min Act: -0.1700
Data Index: 1918460 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.1999. Min Act: -0.1700
Data Index: 8272321 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.1686. Min Act: -0.1700
Data Index: 5214477 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.1374. Min Act: -0.1700
Data Index: 3025098 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.1374. Min Act: -0.1700
Data Index: 3489554 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.1374. Min Act: -0.1700
Data Index: 1049119 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.1374. Min Act: -0.1700
Data Index: 4185993 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.1374. Min Act: -0.1700
Data Index: 8203871 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.1061. Min Act: -0.1700
Data Index: 6508534 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9499. Min Range: -6.9499
Max Act: 6.1061. Min Act: -0.1700
Data Index: 3136829 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19