Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1849 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2230. Min Range: -6.2230
Max Act: 6.2230. Min Act: -0.1700
Data Index: 6273769 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2230. Min Range: -6.2230
Max Act: 6.1605. Min Act: -0.1700
Data Index: 1935095 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.6605. Min Act: -0.1700
Data Index: 6367488 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.5980. Min Act: -0.1700
Data Index: 7697537 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.5667. Min Act: -0.1700
Data Index: 8729586 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.5667. Min Act: -0.1700
Data Index: 1024057 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.5355. Min Act: -0.1700
Data Index: 3028826 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.5042. Min Act: -0.1700
Data Index: 3605046 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.5042. Min Act: -0.1700
Data Index: 4616895 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.5042. Min Act: -0.1700
Data Index: 1921102 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.4730. Min Act: -0.1700
Data Index: 1082109 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.4730. Min Act: -0.1700
Data Index: 1659492 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.4730. Min Act: -0.1700
Data Index: 338713 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.4730. Min Act: -0.1700
Data Index: 6675142 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.4417. Min Act: -0.1700
Data Index: 5321855 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.4417. Min Act: -0.1700
Data Index: 1966792 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.4417. Min Act: -0.1700
Data Index: 5345769 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.4730. Min Act: -0.1700
Data Index: 3766368 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.4417. Min Act: -0.1700
Data Index: 5559454 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2230. Min Range: -6.2230
Max Act: 5.4417. Min Act: -0.1700
Data Index: 4709340 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19