Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3682 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6603. Min Range: -8.6603
Max Act: 8.6603. Min Act: -0.1700
Data Index: 1150559 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6603. Min Range: -8.6603
Max Act: 8.4728. Min Act: -0.1700
Data Index: 1150557 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6603. Min Range: -8.6603
Max Act: 8.4728. Min Act: -0.1700
Data Index: 1150558 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6603. Min Range: -8.6603
Max Act: 8.4103. Min Act: -0.1700
Data Index: 1150555 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6603. Min Range: -8.6603
Max Act: 8.4103. Min Act: -0.1700
Data Index: 8172048 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6603. Min Range: -8.6603
Max Act: 8.3478. Min Act: -0.1700
Data Index: 8172047 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6603. Min Range: -8.6603
Max Act: 8.2540. Min Act: -0.1700
Data Index: 1987109 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6603. Min Range: -8.6603
Max Act: 8.1915. Min Act: -0.1700
Data Index: 863413 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6603. Min Range: -8.6603
Max Act: 8.1915. Min Act: -0.1700
Data Index: 7855523 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6603. Min Range: -8.6603
Max Act: 8.0978. Min Act: -0.1700
Data Index: 5425785 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6603. Min Range: -8.6603
Max Act: 8.0353. Min Act: -0.1700
Data Index: 1868721 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6603. Min Range: -8.6603
Max Act: 8.0040. Min Act: -0.1700
Data Index: 5733541 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6603. Min Range: -8.6603
Max Act: 7.9728. Min Act: -0.1700
Data Index: 5606660 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6603. Min Range: -8.6603
Max Act: 7.9728. Min Act: -0.1700
Data Index: 863414 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6603. Min Range: -8.6603
Max Act: 7.9415. Min Act: -0.1700
Data Index: 7259848 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6603. Min Range: -8.6603
Max Act: 7.9103. Min Act: -0.1700
Data Index: 863415 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6603. Min Range: -8.6603
Max Act: 7.9103. Min Act: -0.1700
Data Index: 5733536 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6603. Min Range: -8.6603
Max Act: 7.8790. Min Act: -0.1700
Data Index: 7790135 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6603. Min Range: -8.6603
Max Act: 7.8478. Min Act: -0.1700
Data Index: 3813784 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6603. Min Range: -8.6603
Max Act: 7.8478. Min Act: -0.1700
Data Index: 1672966 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19