Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1669 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.6165. Min Act: -0.1700
Data Index: 3321028 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.5853. Min Act: -0.1700
Data Index: 1186485 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.5540. Min Act: -0.1700
Data Index: 8791798 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.4915. Min Act: -0.1700
Data Index: 61461 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.5228. Min Act: -0.1700
Data Index: 6819178 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.4915. Min Act: -0.1700
Data Index: 2620943 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.4603. Min Act: -0.1700
Data Index: 7886788 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.4603. Min Act: -0.1700
Data Index: 8624012 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.4603. Min Act: -0.1700
Data Index: 6663869 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.3978. Min Act: -0.1700
Data Index: 4774237 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.3978. Min Act: -0.1700
Data Index: 5830599 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.3978. Min Act: -0.1700
Data Index: 3494965 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.3978. Min Act: -0.1700
Data Index: 936104 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.3978. Min Act: -0.1700
Data Index: 7236683 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.3978. Min Act: -0.1700
Data Index: 6983772 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.3978. Min Act: -0.1700
Data Index: 683377 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.3665. Min Act: -0.1700
Data Index: 2073462 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.3665. Min Act: -0.1700
Data Index: 4623071 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.3665. Min Act: -0.1700
Data Index: 4507837 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6165. Min Range: -5.6165
Max Act: 5.3665. Min Act: -0.1700
Data Index: 6252353 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19