Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4145 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3819. Min Range: -8.3819
Max Act: 8.3819. Min Act: -0.1700
Data Index: 3347135 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3819. Min Range: -8.3819
Max Act: 8.0694. Min Act: -0.1700
Data Index: 629154 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3819. Min Range: -8.3819
Max Act: 8.0069. Min Act: -0.1700
Data Index: 3728561 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3819. Min Range: -8.3819
Max Act: 7.9444. Min Act: -0.1700
Data Index: 6988136 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3819. Min Range: -8.3819
Max Act: 7.9444. Min Act: -0.1700
Data Index: 4546484 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3819. Min Range: -8.3819
Max Act: 7.9444. Min Act: -0.1700
Data Index: 8377399 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3819. Min Range: -8.3819
Max Act: 7.9444. Min Act: -0.1700
Data Index: 2988155 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3819. Min Range: -8.3819
Max Act: 7.9444. Min Act: -0.1700
Data Index: 532675 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3819. Min Range: -8.3819
Max Act: 7.9444. Min Act: -0.1700
Data Index: 1723398 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3819. Min Range: -8.3819
Max Act: 7.8819. Min Act: -0.1700
Data Index: 1313935 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3819. Min Range: -8.3819
Max Act: 7.8819. Min Act: -0.1700
Data Index: 1641577 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3819. Min Range: -8.3819
Max Act: 7.8194. Min Act: -0.1700
Data Index: 6799773 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3819. Min Range: -8.3819
Max Act: 7.8194. Min Act: -0.1700
Data Index: 3792524 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3819. Min Range: -8.3819
Max Act: 7.8194. Min Act: -0.1700
Data Index: 8631101 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3819. Min Range: -8.3819
Max Act: 7.8194. Min Act: -0.1700
Data Index: 8502903 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3819. Min Range: -8.3819
Max Act: 7.8194. Min Act: -0.1700
Data Index: 2313084 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3819. Min Range: -8.3819
Max Act: 7.7569. Min Act: -0.1700
Data Index: 1065316 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3819. Min Range: -8.3819
Max Act: 7.7569. Min Act: -0.1700
Data Index: 8138360 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3819. Min Range: -8.3819
Max Act: 7.6944. Min Act: -0.1700
Data Index: 2749233 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3819. Min Range: -8.3819
Max Act: 7.6944. Min Act: -0.1700
Data Index: 5557371 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19