Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2772 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.7935. Min Act: -0.1700
Data Index: 5191883 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.7935. Min Act: -0.1700
Data Index: 6343373 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.7623. Min Act: -0.1700
Data Index: 1153199 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.6684. Min Act: -0.1700
Data Index: 8694328 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.6371. Min Act: -0.1700
Data Index: 574438 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.5902. Min Act: -0.1700
Data Index: 3001921 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.5902. Min Act: -0.1700
Data Index: 3620021 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.5745. Min Act: -0.1700
Data Index: 445103 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.5589. Min Act: -0.1700
Data Index: 344186 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.5589. Min Act: -0.1700
Data Index: 8098953 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.5589. Min Act: -0.1700
Data Index: 153662 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.5432. Min Act: -0.1700
Data Index: 3017165 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.5119. Min Act: -0.1700
Data Index: 6250150 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.5119. Min Act: -0.1700
Data Index: 3939918 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.5119. Min Act: -0.1700
Data Index: 968333 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.5119. Min Act: -0.1700
Data Index: 2771743 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.4962. Min Act: -0.1700
Data Index: 6656302 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.4962. Min Act: -0.1700
Data Index: 6792717 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.4806. Min Act: -0.1700
Data Index: 7074018 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7935. Min Range: -3.7935
Max Act: 3.4806. Min Act: -0.1700
Data Index: 2518834 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19