Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3791 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.9786. Min Act: -0.1700
Data Index: 870932 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.7911. Min Act: -0.1700
Data Index: 8755158 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.7286. Min Act: -0.1700
Data Index: 4112882 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.6036. Min Act: -0.1700
Data Index: 2964601 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.6661. Min Act: -0.1700
Data Index: 6117840 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.5724. Min Act: -0.1700
Data Index: 5679164 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.6036. Min Act: -0.1700
Data Index: 1816615 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.5724. Min Act: -0.1700
Data Index: 872272 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.5099. Min Act: -0.1700
Data Index: 1102401 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.5099. Min Act: -0.1700
Data Index: 170831 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.5099. Min Act: -0.1700
Data Index: 1345675 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.4474. Min Act: -0.1700
Data Index: 804874 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.4474. Min Act: -0.1700
Data Index: 4403791 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.4786. Min Act: -0.1700
Data Index: 4570747 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.4474. Min Act: -0.1700
Data Index: 5820802 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.3849. Min Act: -0.1700
Data Index: 2910943 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.3849. Min Act: -0.1700
Data Index: 4866391 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.3849. Min Act: -0.1700
Data Index: 1389361 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.3849. Min Act: -0.1700
Data Index: 5673585 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9786. Min Range: -8.9786
Max Act: 8.3849. Min Act: -0.1700
Data Index: 3074490 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19