Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 159 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3669. Min Range: -4.3669
Max Act: 4.3669. Min Act: -0.1700
Data Index: 3412357 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3669. Min Range: -4.3669
Max Act: 4.0857. Min Act: -0.1700
Data Index: 1505908 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3669. Min Range: -4.3669
Max Act: 4.1169. Min Act: -0.1700
Data Index: 5389616 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3669. Min Range: -4.3669
Max Act: 4.0857. Min Act: -0.1700
Data Index: 3173337 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3669. Min Range: -4.3669
Max Act: 4.0544. Min Act: -0.1700
Data Index: 519148 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3669. Min Range: -4.3669
Max Act: 4.0544. Min Act: -0.1700
Data Index: 2216849 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3669. Min Range: -4.3669
Max Act: 4.0231. Min Act: -0.1700
Data Index: 6363326 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3669. Min Range: -4.3669
Max Act: 3.9919. Min Act: -0.1700
Data Index: 5839502 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3669. Min Range: -4.3669
Max Act: 3.9919. Min Act: -0.1700
Data Index: 6212229 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3669. Min Range: -4.3669
Max Act: 3.9606. Min Act: -0.1700
Data Index: 7068328 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3669. Min Range: -4.3669
Max Act: 3.9606. Min Act: -0.1700
Data Index: 1738032 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3669. Min Range: -4.3669
Max Act: 3.9606. Min Act: -0.1700
Data Index: 107107 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3669. Min Range: -4.3669
Max Act: 3.9606. Min Act: -0.1700
Data Index: 5014449 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3669. Min Range: -4.3669
Max Act: 3.9137. Min Act: -0.1700
Data Index: 5299166 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3669. Min Range: -4.3669
Max Act: 3.9294. Min Act: -0.1700
Data Index: 7300391 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3669. Min Range: -4.3669
Max Act: 3.9294. Min Act: -0.1700
Data Index: 4492726 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3669. Min Range: -4.3669
Max Act: 3.8981. Min Act: -0.1700
Data Index: 6117480 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3669. Min Range: -4.3669
Max Act: 3.8981. Min Act: -0.1700
Data Index: 4285702 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3669. Min Range: -4.3669
Max Act: 3.8825. Min Act: -0.1700
Data Index: 3517005 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3669. Min Range: -4.3669
Max Act: 3.8981. Min Act: -0.1700
Data Index: 7298714 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19