Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3652 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1862. Min Range: -8.1862
Max Act: 8.1862. Min Act: -0.1700
Data Index: 8491606 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.9987. Min Act: -0.1700
Data Index: 5518445 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.8737. Min Act: -0.1700
Data Index: 566862 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.8737. Min Act: -0.1700
Data Index: 1281979 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.8112. Min Act: -0.1700
Data Index: 2337527 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.7487. Min Act: -0.1700
Data Index: 1304776 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.6862. Min Act: -0.1700
Data Index: 1078075 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.6862. Min Act: -0.1700
Data Index: 3010909 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.6862. Min Act: -0.1700
Data Index: 6459124 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.6237. Min Act: -0.1700
Data Index: 3231864 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.6237. Min Act: -0.1700
Data Index: 7464899 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.6237. Min Act: -0.1700
Data Index: 4163420 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.5924. Min Act: -0.1700
Data Index: 7542494 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.5612. Min Act: -0.1700
Data Index: 962350 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.5612. Min Act: -0.1700
Data Index: 5637676 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.5612. Min Act: -0.1700
Data Index: 7640688 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.5924. Min Act: -0.1700
Data Index: 5948609 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.4987. Min Act: -0.1700
Data Index: 2447980 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.5299. Min Act: -0.1700
Data Index: 3646608 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1862. Min Range: -8.1862
Max Act: 7.4987. Min Act: -0.1700
Data Index: 7297939 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19