Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1889 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4719. Min Range: -6.4719
Max Act: 6.4719. Min Act: -0.1700
Data Index: 8779755 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4719. Min Range: -6.4719
Max Act: 6.3782. Min Act: -0.1700
Data Index: 2322312 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4719. Min Range: -6.4719
Max Act: 6.3469. Min Act: -0.1700
Data Index: 182849 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4719. Min Range: -6.4719
Max Act: 6.2844. Min Act: -0.1700
Data Index: 5517886 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4719. Min Range: -6.4719
Max Act: 6.2532. Min Act: -0.1700
Data Index: 1933243 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4719. Min Range: -6.4719
Max Act: 6.2219. Min Act: -0.1700
Data Index: 8092701 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4719. Min Range: -6.4719
Max Act: 6.2532. Min Act: -0.1700
Data Index: 4861820 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4719. Min Range: -6.4719
Max Act: 6.2219. Min Act: -0.1700
Data Index: 6208897 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4719. Min Range: -6.4719
Max Act: 6.1907. Min Act: -0.1700
Data Index: 8817501 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4719. Min Range: -6.4719
Max Act: 6.1594. Min Act: -0.1700
Data Index: 8092702 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4719. Min Range: -6.4719
Max Act: 6.1594. Min Act: -0.1700
Data Index: 1017446 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4719. Min Range: -6.4719
Max Act: 6.0657. Min Act: -0.1700
Data Index: 6208896 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4719. Min Range: -6.4719
Max Act: 6.0657. Min Act: -0.1700
Data Index: 8092704 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4719. Min Range: -6.4719
Max Act: 6.0657. Min Act: -0.1700
Data Index: 4177 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4719. Min Range: -6.4719
Max Act: 6.0032. Min Act: -0.1700
Data Index: 4228431 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4719. Min Range: -6.4719
Max Act: 5.9719. Min Act: -0.1700
Data Index: 8668606 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4719. Min Range: -6.4719
Max Act: 5.9719. Min Act: -0.1700
Data Index: 1380941 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4719. Min Range: -6.4719
Max Act: 5.9094. Min Act: -0.1700
Data Index: 4161166 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4719. Min Range: -6.4719
Max Act: 5.9094. Min Act: -0.1700
Data Index: 1309103 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4719. Min Range: -6.4719
Max Act: 5.9094. Min Act: -0.1700
Data Index: 8175558 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19