Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1869 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.8032. Min Act: -0.1700
Data Index: 7993103 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.6782. Min Act: -0.1700
Data Index: 6936084 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.6782. Min Act: -0.1700
Data Index: 6025599 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.6469. Min Act: -0.1700
Data Index: 5584691 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.6157. Min Act: -0.1700
Data Index: 5584715 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.5532. Min Act: -0.1700
Data Index: 5761689 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.5219. Min Act: -0.1700
Data Index: 8512705 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4907. Min Act: -0.1700
Data Index: 4879658 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.4281. Min Act: -0.1700
Data Index: 8209876 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.3969. Min Act: -0.1700
Data Index: 3735670 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.3969. Min Act: -0.1700
Data Index: 341042 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.3969. Min Act: -0.1700
Data Index: 123679 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.3969. Min Act: -0.1700
Data Index: 7452319 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.3656. Min Act: -0.1700
Data Index: 2351049 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.3344. Min Act: -0.1700
Data Index: 4111949 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.3344. Min Act: -0.1700
Data Index: 6224779 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.3344. Min Act: -0.1700
Data Index: 2785393 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.3031. Min Act: -0.1700
Data Index: 7666431 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.2719. Min Act: -0.1700
Data Index: 1160417 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8032. Min Range: -4.8032
Max Act: 4.2719. Min Act: -0.1700
Data Index: 3667084 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19