Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2757 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.5987. Min Act: -0.1700
Data Index: 52100 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.5049. Min Act: -0.1700
Data Index: 989750 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.5049. Min Act: -0.1700
Data Index: 7119603 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.4424. Min Act: -0.1700
Data Index: 7880587 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.4112. Min Act: -0.1700
Data Index: 1188844 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.4112. Min Act: -0.1700
Data Index: 8749881 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.3487. Min Act: -0.1700
Data Index: 8712254 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.2862. Min Act: -0.1700
Data Index: 1774393 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.2862. Min Act: -0.1700
Data Index: 3380231 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.2549. Min Act: -0.1700
Data Index: 1890927 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.3174. Min Act: -0.1700
Data Index: 7259965 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.3174. Min Act: -0.1700
Data Index: 8743008 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.2549. Min Act: -0.1700
Data Index: 4309525 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.2237. Min Act: -0.1700
Data Index: 5003337 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.2549. Min Act: -0.1700
Data Index: 3303083 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.2237. Min Act: -0.1700
Data Index: 3359530 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.2237. Min Act: -0.1700
Data Index: 7070186 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.1924. Min Act: -0.1700
Data Index: 1000948 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.1924. Min Act: -0.1700
Data Index: 1504715 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5987. Min Range: -7.5987
Max Act: 7.1924. Min Act: -0.1700
Data Index: 5480787 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19