Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.8262. Min Act: -0.1700
Data Index: 7078902 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.7012. Min Act: -0.1700
Data Index: 1631083 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.7012. Min Act: -0.1700
Data Index: 8110055 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.4512. Min Act: -0.1700
Data Index: 7732727 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.3887. Min Act: -0.1700
Data Index: 5335673 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.3575. Min Act: -0.1700
Data Index: 1083771 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.3575. Min Act: -0.1700
Data Index: 6137160 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.3262. Min Act: -0.1700
Data Index: 6990094 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.3262. Min Act: -0.1700
Data Index: 6556967 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.2325. Min Act: -0.1700
Data Index: 4240658 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.2325. Min Act: -0.1700
Data Index: 1297549 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.2012. Min Act: -0.1700
Data Index: 5927449 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.2325. Min Act: -0.1700
Data Index: 1043750 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.1387. Min Act: -0.1700
Data Index: 7806142 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.1387. Min Act: -0.1700
Data Index: 2224083 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.1387. Min Act: -0.1700
Data Index: 362494 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.1075. Min Act: -0.1700
Data Index: 4144239 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.0762. Min Act: -0.1700
Data Index: 4658928 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.1387. Min Act: -0.1700
Data Index: 750432 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8262. Min Range: -7.8262
Max Act: 7.0762. Min Act: -0.1700
Data Index: 565848 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19