Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5970 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3074. Min Range: -5.3074
Max Act: 5.3074. Min Act: -0.1700
Data Index: 5560891 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.9636. Min Act: -0.1700
Data Index: 1881412 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.8699. Min Act: -0.1700
Data Index: 4944979 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.8699. Min Act: -0.1700
Data Index: 8099767 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.8386. Min Act: -0.1700
Data Index: 2606585 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.7761. Min Act: -0.1700
Data Index: 1075380 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.7449. Min Act: -0.1700
Data Index: 7360150 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.7449. Min Act: -0.1700
Data Index: 5153208 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.7761. Min Act: -0.1700
Data Index: 112743 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.7449. Min Act: -0.1700
Data Index: 7389074 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.7136. Min Act: -0.1700
Data Index: 2203621 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.6824. Min Act: -0.1700
Data Index: 2668224 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.6824. Min Act: -0.1700
Data Index: 8758678 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.6824. Min Act: -0.1700
Data Index: 8582062 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.6511. Min Act: -0.1700
Data Index: 172142 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.6511. Min Act: -0.1700
Data Index: 7404022 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.6511. Min Act: -0.1700
Data Index: 2281773 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.6511. Min Act: -0.1700
Data Index: 3171757 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.6824. Min Act: -0.1700
Data Index: 368615 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3074. Min Range: -5.3074
Max Act: 4.6199. Min Act: -0.1700
Data Index: 5855714 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19