Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4287 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.8762. Min Act: -0.1700
Data Index: 587633 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.6887. Min Act: -0.1700
Data Index: 8210955 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.5637. Min Act: -0.1700
Data Index: 5035876 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.5012. Min Act: -0.1700
Data Index: 2090640 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.5012. Min Act: -0.1700
Data Index: 1235843 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.5012. Min Act: -0.1700
Data Index: 6929259 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.4387. Min Act: -0.1700
Data Index: 6818488 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.3762. Min Act: -0.1700
Data Index: 7773911 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.3762. Min Act: -0.1700
Data Index: 3746407 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.3137. Min Act: -0.1700
Data Index: 6620091 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.3137. Min Act: -0.1700
Data Index: 3366555 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.3137. Min Act: -0.1700
Data Index: 816748 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.2512. Min Act: -0.1700
Data Index: 5719267 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.2512. Min Act: -0.1700
Data Index: 2017928 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.2512. Min Act: -0.1700
Data Index: 8571673 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.1887. Min Act: -0.1700
Data Index: 710265 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.1887. Min Act: -0.1700
Data Index: 846810 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.1887. Min Act: -0.1700
Data Index: 1297029 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.1887. Min Act: -0.1700
Data Index: 4012514 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8762. Min Range: -9.8762
Max Act: 9.1887. Min Act: -0.1700
Data Index: 5570982 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19